* Add copilot-pr-autopilot skill
Skill that drives any GitHub pull request through repeated rounds of
Copilot Code Review until the agent has either resolved every thread
or explicitly escalated it to the human. Triggered via GraphQL (no
@copilot mention needed), triages every open thread with a fix /
decline / escalate rubric, replies and resolves each thread citing
the pushed SHA, then re-triggers until HEAD is reviewed with zero
threads awaiting the agent's reply.
Includes step scripts (01 request-review, 02 check-review-status,
03 list-open-threads, 08 reply-and-resolve, 10 cleanup-outdated),
shared library (_lib.ps1) with gh-CLI wrappers (Invoke-Gh,
Invoke-GhGraphQL, ConvertFrom-GhJson, Assert-GhReady), reply
templates, and reference docs for each step.
Repo-agnostic. Requires gh CLI on PATH and repo Triage/Write for
full autopilot; external PR authors get single-iteration mode with
manual re-trigger via the UI re-request button or a substantive
push.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Address review: split per-step references + add recap-gate circuit breaker
- Fix#1: give steps 1/7/10 their own reference files
(01-request-review.md, 07-commit-push.md, 10-cleanup.md); trim the
inline bodies out of orchestration.md so it stays cross-cutting only.
- Fix#3: add a recurring round-cap & recap gate to 09-convergence.md —
default STOP every 10th round, recap all prior rounds, detect drift
(out-of-scope / over-engineering / wrong-direction / belongs-in-separate-PR)
with CONTINUE / REVERT-AND-SHIP / HAND-OFF verdicts. Agent reasoning,
no new script.
- Surface the gate from SKILL.md and orchestration.md; regenerate
docs/README.skills.md. Markdown-only change; scripts unchanged.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* docs(copilot-pr-autopilot): surface recap gate in decision pseudo-code; clarify Copilot+human convergence and round definition
- Inject the round-cap recap gate into the '## Decision: loop back or exit'
pseudo-code else-branch so an agent following the code block (not just the
prose) runs the STOP-every-10th-round check before looping.
- Broaden the 'never terminal' paragraph: non-convergence is driven by a
Copilot finding OR a human review comment (this skill handles both); the
loop ends only when there are no new comments from either source AND every
open thread (Copilot or human) has an agent reply/escalation.
- Define a 'round' explicitly as one execution of step 1 (01-request-review),
i.e. one Copilot-review trigger — the cap counts review rounds, not tool
calls or fix edits.
Markdown-only; no script changes.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* copilot-pr-autopilot: make recap-gate round count deterministic
Add 09-review-round.ps1: counts Copilot Code Review submissions straight
from the PR's API history (full GraphQL pagination), so the recap-gate
trigger is a derived number, not a fallible agent mental tally. This
removes the exact failure mode the skill exists to survive — a count
drifting across a long run (the real 156-round case).
The script reports Round + RecapDue (Round % RecapInterval == 0) only;
it never stops the loop or picks the verdict. CONTINUE / REVERT-AND-SHIP
/ HAND-OFF stays agent reasoning. 09-convergence.md updated to reference
the deterministic count while preserving 'no script stops the loop' and
'non-convergence = Copilot finding OR human comment'.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Regenerate docs/README.skills.md for copilot-pr-autopilot (add 09-review-round.ps1)
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
---------
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* azure-devops-cli: handle long comments on Windows (#2061)
On Windows 'az' is a cmd.exe batch wrapper capped at ~8191 characters,
so a long --discussion / --description value silently truncates or
fails. Document three verified ways out so the coding agent doesn't
waste 3-5 turns falling back to raw token retrieval and REST:
1. azps.ps1 in PowerShell on Windows. Same Azure CLI, invoked through
the Python entry point with no cmd.exe length cap. Pair with
'Get-Content -Raw' so the body lives in a variable, not on the
command line.
2. Native --file-path flags where Azure CLI offers them. Applies to
'az devops wiki page create' and 'az devops wiki page update', both
documented with --encoding.
3. 'az devops invoke --in-file' as the universal escape hatch for
commands with no --file-path (work-item --discussion, PR
--description). Documented example posts to the work item
comments REST endpoint with api-version 7.0-preview.3.
The earlier draft suggested the Azure CLI '@<file>' convention as a
generic substitute for inline string args. The official docs only
document it for JSON parameters and the CLI source uses
'get_file_json' specifically, so the claim is removed and replaced
with an explicit warning not to rely on it for plain string args.
Files touched:
- skills/azure-devops-cli/SKILL.md: new 'Posting long comments on
Windows' section with shell-detection table and three verified
options.
- skills/azure-devops-cli/references/boards-and-iterations.md: short
pointer at each --discussion example back to SKILL.md, plus an
inline PowerShell snippet.
Closes#2061.
* azure-devops-cli: move long-comments guidance to reference file (#2061 review)
aaronpowell asked for the Windows long-comments section to live as a
reference file rather than inline in SKILL.md, so the token weight
isn't always loaded into the agent's context.
- Move the "Posting long comments on Windows" section to a new
references/long-comments-on-windows.md verbatim.
- Strip the section from SKILL.md (56 fewer lines in the always-loaded
surface).
- Add the new file to the Reference Files table in SKILL.md with a
one-line "when to read" hint covering --discussion, --description,
and --content failures on Windows.
- Update the two pointer comments in references/boards-and-iterations.md
to point at the new reference file instead of the SKILL.md section.
docs/README.skills.md regenerated by 'npm run build' to pick up the
new reference file in the skill's bundled assets column.
The `name` frontmatter was `AWS CloudWatch Investigation`, which violated the Agent Skills spec and failed `npm run skill:validate` on main: name must be lowercase letters, numbers, and hyphens and must match the folder name (`aws-cloudwatch-investigation`). Correct the name and regenerate docs/README.skills.md so the validator passes (365/365) and the skills table renders consistently with every other entry.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* feat: add technical job search instructions for CV tailoring, cover letters, and offer evaluation
* chore: regenerate README.instructions.md after adding job search instructions
* refactor: convert technical-job-search from instruction to skill
Per reviewer feedback, instructions load on every turn and waste tokens
for content that is only useful during active job search sessions. A skill
is opted into explicitly, making this a better fit.
- Remove instructions/technical-job-search.instructions.md
- Add skills/technical-job-search/SKILL.md with equivalent content
- Update docs/README.instructions.md and docs/README.skills.md
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* chore: regenerate README.skills.md
---------
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
* Add setup-my-iq skill
* Use forward-slash separators in setup-my-iq context pointers for cross-platform portability
* Fix stale step references (9c->10c, 9d->10d) in setup-my-iq SKILL.md
* aws plugin and adding few more aws agents
* updating the agent def
* fixed around skill validator results.
---------
Co-authored-by: Preyas Prakasan <preyasprakasan@Preyass-MacBook-Pro.local>
Replace the Bash namecheap.sh with a stdlib-only Python CLI (namecheap.py)
that resolves all Copilot PR review feedback:
- Cache the public IP once per run instead of per request
- Build API requests in-process via urllib so the API key never appears
in process argv or shell history
- Broaden multi-part TLD detection (co.uk, com.au, etc.) and document the
limitation
- Allow setup to update existing stored credentials
- Stop soliciting the API key via chat; use terminal getpass or env vars
- Remove non-portable Bash constructs (inline local, grep -oP)
Also normalize domain casing, preserve MX priority 0, accept
case-insensitive record types, and handle mixed-case email-forwarding
attributes. Update SKILL.md and regenerate the skills README.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* feat: add conventional-branch skill
Add a new agent skill for creating Git branches following the
Conventional Branch specification. The skill covers branch naming
rules, valid/invalid examples, type prefixes (feature/, bugfix/,
hotfix/, release/, chore/), trunk branch detection, and a
step-by-step workflow for branch creation.
The skill complements the existing conventional-commit skill and
references the specification at https://conventional-branch.github.io.
* fix: use explicit numbered workflow steps in conventional-branch skill
Replace markdown heading-based workflow steps (### 1., ### 2.)
with explicit 'Step N — Title' format for better agent
comprehension.
* Add visual-pr plugin: screenshot capture, annotation, PR embedding, and screen recording
Four skills that teach Copilot to capture UI screenshots (Playwright + PIL),
annotate them with algorithmic label placement, embed before/after images
in PR descriptions, and record animated GIF demos.
Includes demo images showing the annotation engine on GitHub Issues.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Update generated README tables and marketplace.json
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Embed annotate.py module in image-annotations skill
The full working module (annotate_image, grid_image, diff_images) is now
included as a code block so users can save it as annotate.py and import
directly. Scrubbed project-specific labels from examples.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Address review feedback: mss.mss() context manager, fix RECT struct, consistent placeholder
- Use mss.mss() context manager instead of mss.MSS() (ui-screenshots, screen-recording)
- Fix broken RECT struct in window+GIF combining example (screen-recording)
- Consistent projectId placeholder in AzDO upload example (pr-screenshots)
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
---------
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* fresh pull of updated stage with 2 skills and updated README only
* adjusted skills after feedback and used skill analyser to review
---------
Co-authored-by: Mark Heynes <mutl3y@heynes.biz>
Adds a skill that lets users generate images (icons, sprites, textures,
mockups) directly from their coding workflow using OpenAI gpt-image-2 or
Google Gemini. BYO API key — the skill guides users through setup on
first use.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* feat: add prompt-optimizer skill for enhancing prompt quality in chat interfaces
* Potential fix for pull request finding
Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>
* fix: update prompt handling to include clarifying questions for incomplete requests
---------
Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>
Remove all bundled polyglot-test-agent content (8 agents, 1 skill,
plugin metadata) and add dotnet-test as an external plugin from
dotnet/skills. The external plugin is a superset (11 agents, 22 skills).
Marketplace and doc indexes regenerated via npm run build.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Add complete skill for Slang shader language
- Included the full Offical Slang LLM documentation.
- Included sections on language features, interfaces, generics, automatic differentiation, modules, capabilities system, compiling code, reflection API, compilation targets, and FAQs.
- Allows agents to write comprehensive slang code for graphics and compute shaders.
* Fix for conflicting description matches established skill conventions
Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>
---------
Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>
Rebuilds branch from upstream/staged (was previously merged from
upstream/main, which brought in materialized plugin files that
fail Check Plugin Structure on PRs targeting staged).
Changes vs. staged:
- Update skills/quality-playbook/ to v1.5.6 (31 bundled assets:
SKILL.md + LICENSE.txt + 16 references/ + 9 phase_prompts/ +
3 agents/ + bin/citation_verifier.py + quality_gate.py).
- Add agents/quality-playbook.agent.md (top-level orchestrator).
name: quality-playbook (validator-compliant).
- Update docs/README.skills.md quality-playbook row description
+ bundled-assets list to v1.5.6.
- Fix 'unparseable' → 'unparsable' in quality_gate.py (5 instances;
codespell preference, both spellings valid).
Closes the v1.4.0 → v1.5.6 update in a single clean commit on top of
upstream/staged. The preserved backup branch backup-bedbe84-pre-rebuild
(SHA bedbe848fa3c0f0eda8e653c42b599a17dd2e354) holds the prior history for reference.
* feat(flowstudio): align Power Automate skills with MCP server v1.1.6
Foundation skill (flowstudio-power-automate-mcp) rewritten to use the
server's new tool_search and list_skills meta-tools (v1.1.5+) for
discovery instead of cataloging every tool by hand. Cut from 519 to
295 lines. New "Which Skill to Use When" intent-keyed decision tree
points at the four specialized skills.
Build/debug/governance/monitoring updated for use-case framing. Tools
that genuinely cross tiers (e.g. debug skill borrowing
get_store_flow_summary) are correct when the workflow needs them — the
split between skills is by use-case intent, not by tool partition.
Build skill: new Step 3a Resolving Dynamic Connector Values covers
get_live_dynamic_options outer-parameter auto-bridge (v1.1.6+) and the
AadGraph user-picker fallback via shared_office365users.SearchUserV2
(replaces broken builtInOperation:AadGraph.GetUsers).
Debug skill: Outlook user-picker failure note pointing at the fallback.
Monitoring skill description disambiguates from the server's monitor-flow
tool bundle (runtime control of a single flow) — this skill is
tenant-wide health analytics over the cached store.
All 5 skills validate via npm run skill:validate; line endings LF only;
codespell clean; auto-regenerated docs/README.skills.md included.
* fix(flowstudio): remove deprecated tool references
The v1.1.5 MCP server release marked 5 tools [DEPRECATED] but the
previous alignment commit missed them. Replacements per server source:
- get_live_flow_http_schema → read trigger.inputs.schema from get_live_flow
- get_live_flow_trigger_url → read trigger.metadata.callbackUrl from get_live_flow
- get_store_flow_trigger_url → get_store_flow.triggerUrl field
- get_store_flow_errors → get_store_flow_runs(status=["Failed"])
- set_store_flow_state → set_live_flow_state
Touches build, debug, governance, monitoring SKILL.md and the
foundation skill's tool-reference.md. Remaining mentions of the
deprecated names are intentional — they live in deprecation notices
naming the obsolete wrapper alongside its replacement.
* Update FlowStudio Power Automate skills
* Cover latest FlowStudio MCP actions
* Trim FlowStudio Power Automate skills
* Number FlowStudio build workflow steps
* feat(skills): add dotnet-mcp-builder, deprecate csharp-mcp-server-generator
Adds a comprehensive skill for building MCP (Model Context Protocol)
servers in C#/.NET against the official ModelContextProtocol 1.x NuGet
packages. Covers both transports (STDIO, Streamable HTTP — SSE is
deprecated) and every primitive in the current MCP spec (2025-11-25):
tools, prompts, resources, elicitation (form + URL mode), sampling,
roots, completions, logging, and MCP Apps. Includes a thin .NET MCP
client reference and testing guidance (MCP Inspector + in-memory
transport for unit tests).
Steers the model toward the current stable 1.x packages instead of the
0.x previews it tends to pin by default, and enforces the STDIO
stdout/stderr trap.
Also deprecates the existing csharp-mcp-server-generator skill, which
predates ModelContextProtocol 1.0 and only covered a subset of the
current spec. Its SKILL.md now redirects users to dotnet-mcp-builder so
existing install URLs keep working without surprises.
* fix: address PR review from aaronpowell
- Delete csharp-mcp-server-generator skill (rather than deprecating it)
- Update mcp-apps.md pitfalls section to reference .NET Tool.Meta type
instead of the serialized _meta JSON property names
- Rebuild docs/README.skills.md
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* chore: remove C# MCP development plugin files
* chore: remove csharp-mcp-development plugin entry from marketplace
---------
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Add acreadiness-cockpit plugin
Adds a new plugin that drives Microsoft AgentRC from Copilot chat,
framing every interaction inside AgentRC's Measure -> Generate ->
Maintain loop.
Custom agent (agents/ai-readiness-reporter.agent.md):
Runs `agentrc readiness --json`, interprets every result against
the 9-pillar / 5-level maturity model, then renders a self-contained
reports/index.html from a fixed HTML/CSS template (bundled with the
acreadiness-assess skill) so every user gets an identically styled
dashboard. Honours policies (disabled criteria, overrides, pass-rate
thresholds) and surfaces extras separately.
Skills:
- acreadiness-assess: Measure step. Wraps `agentrc readiness --json`
and hands off to the @ai-readiness-reporter agent. Bundles the
canonical report-template.html.
- acreadiness-generate-instructions: Generate step. Wraps
`agentrc instructions`. Defaults to .github/copilot-instructions.md
(Copilot-native). Asks flat vs nested. For monorepos, emits per-area
.github/instructions/<area>.instructions.md files with applyTo
globs taken from agentrc.config.json.
- acreadiness-policy: Maintain step. Helps pick, scaffold, or apply an
AgentRC policy (criteria.disable, criteria.override, extras,
thresholds) and wire it into CI via --fail-level.
Plugin (plugins/acreadiness-cockpit/):
Declarative plugin.json referencing the agent and three skills.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* Address PR review feedback
- Align documented slash-command names with plugin manifest:
/acreadiness-assess, /acreadiness-generate-instructions,
/acreadiness-policy (was /assess, /generate-instructions, /policy
inside SKILL bodies and argument-hints).
- Move the literal % from the report template into the substituted
values for {{passRate}} and {{threshold}} so an N/A value of '—'
no longer renders as '—%'. Updated the agent placeholder contract
accordingly.
- Point the report footer at the canonical plugin folder under
github/awesome-copilot instead of the personal source fork.
- Add explicit HTML-escaping rules to the agent: HTML-escape every
{{placeholder}} substitution, and replace </script with <\/script
inside the embedded JSON block so untrusted repo content cannot
break the markup or inject scripts.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
---------
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Gordon Lam
Komal Vardhan Lolugu
Sukanth Gunda
Burak Bayır
Mammon Baloch
Lavkesh Dwivedi
Andreas Schnapp
James Montemagno
John Haugabook
sudeepghatak
LakshmiStoltz
Yuan
Amir
Hatsumi Kikuchi
Muhammad Furqan
Preyas Prakasan
Bruno Borges
Xianpeng Shen
AlisonMacLellanCreates
Mikael
Jakub Jareš
mutl3y
Aaron Powell
Kaps
JordanSOA
Adam
Jaylyn Barbee
Lovy Jain
MUHAMMAD SAMIULLAH
Jim Bennett
Jakub Jareš
Thomas Ray
Joseph Kasprzyk
Andrew Stellman
Alvin Ashcraft
Catherine Han
Adrien Clerbois
Jeonghoon Lee
Copilot
Alejandro Fernando Suarez Gomez
Nixon Kurian
Kweku Dzata
mvanderbend-msoft