New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Instructor QA

by cognesy in cognesy/instructor-php

Run multi-dimensional quality assurance for InstructorPHP. An agent skill from cognesy/instructor-php.

MITAuto-check passedTesting & QA

Install Instructor QA

skills CLI
$ npx skills add cognesy/instructor-php --skill instructor-qa -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install cognesy/instructor-php instructor-qa --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/cognesy/instructor-php.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.codex/skills/instructor-qa .claude/skills/instructor-qa && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
instructor-qa
GitHub stars
328
Token cost
~1.3k tokens
SKILL.md length
675 words
Files
3 (incl. references)
Skills in repo
3
Repo updated
First seen
Licence
MIT

At a glance

Run multi-dimensional quality assurance for InstructorPHP. An agent skill from cognesy/instructor-php.

  • Works in 6 steps: Read the request, changed files, and the… → Identify risk shape → Choose the minimum verification bundle… → …
  • Asked to validate a change
  • SKILL.md covers When To Use, Working Model, Default Execution Flow and Deterministic bd Path, plus 2 more sections
  • Calls composer

What it does

Instructor QA is an agent skill from cognesy/instructor-php. Run multi-dimensional quality assurance for InstructorPHP. Use when asked to validate a change, assess production readiness, reproduce CI failures, harden a PR, choose the right verification commands, or investigate regressions across tests, static analysis, docs QA, dependency compatibility, and local GitHub Actions workflow runs.

Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files, including reference files (for example `agents/openai.yaml` and `references/scenarios.md`).

It sits in Testing & QA, covering Static analysis and SAST, QA and bug reports and Failing and flaky tests. It works with GitHub Actions and PHP. The repository describes itself as: Unified LLM API, structured data outputs with LLMs, and agent SDK - in PHP. The licence is MIT.

When your agent uses it

  • Asked to validate a change
  • Assess production readiness
  • Reproduce CI failures
  • Choose the right verification commands

Example prompts

  • “/instructor-qa”

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

  1. Read the request, changed files, and the relevant sections of QUALITY.md.
  2. Identify risk shape
  3. Choose the minimum verification bundle that can falsify the risky assumptions.
  4. Run checks from fast/high-signal to broader/slower.
  5. Separate failures caused by the current change from pre-existing repository debt.
  6. Report exactly what ran, what passed, what failed, what was skipped, and the residual risk.

What it can do on your machine

Read from SKILL.md and the folder at commit 4a5a54d. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • composer

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Instructor QA loads about 1.3k tokens when it runs, and up to ~2.3k if it reads all its reference files. Until then it costs about 87 tokens; SKILL.md has 675 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~87
When it runs · the whole SKILL.md, loaded when a task matches
~1.3k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~2.3k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from cognesy/instructor-php at commit 4a5a54d, republished under its MIT licence (© cognesy). 675 words, ~1,327 tokens.

Download SKILL.mdSave it as .claude/skills/instructor-qa/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.
name
instructor-qa
description
Run multi-dimensional quality assurance for InstructorPHP. Use when asked to validate a change, assess production readiness, reproduce CI failures, harden a PR, choose the right verification commands, or investigate regressions across tests, static analysis, docs QA, dependency compatibility, and local GitHub Actions workflow runs.

Instructor QA

This skill is the repo-local quality assurance specialist for InstructorPHP. It chooses the smallest sufficient verification set for simple work, and for complex or multi-step QA it turns the work into a deterministic bd plan and executes it methodically.

Treat these files as source of truth:

  • QUALITY.md for verification lanes and command entrypoints
  • CONTRIBUTING.md for contributor workflow expectations
  • AGENTS.md for repo-specific operating rules and bd usage
  • .github/workflows/php.yml for the compatibility matrix
  • .actrc for local act defaults

Read references/scenarios.md when you need the scenario-to-command mapping or the complex QA playbooks.

When To Use

Use this skill when the user asks to:

  • run QA or decide which checks to run
  • validate a feature, fix, refactor, dependency upgrade, or release candidate
  • investigate a failing test, linter, docs QA run, or GitHub Actions workflow
  • reproduce CI locally with act
  • assess regression risk, production readiness, or verification gaps
  • audit quality across multiple packages, layers, or tooling lanes

Working Model

Start by classifying the request into one or more QA lanes:

  • behavior tests: composer test, composer test-all, targeted Pest runs
  • integration and live-backend validation: telemetry interop and other opt-in suites
  • static analysis: PHPStan, Psalm, dead-code, unused dependency checks
  • structural and policy checks: Pint, Semgrep
  • docs quality: composer qa:docs, docs drift, and composer qa:docs-sites for deployable-site changes
  • dependency and compatibility validation: Composer resolution plus workflow matrix cells
  • CI and workflow reproduction: act against .github/workflows/php.yml
  • performance: PHPBench

Prefer the smallest sufficient lane set first. Expand only when the risk profile justifies it.

Default Execution Flow

  1. Read the request, changed files, and the relevant sections of QUALITY.md.
  2. Identify risk shape:
    • local implementation
    • docs/examples
    • dependency or Composer manifest change
    • workflow or CI change
    • cross-package or release-sensitive change
  3. Choose the minimum verification bundle that can falsify the risky assumptions.
  4. Run checks from fast/high-signal to broader/slower.
  5. Separate failures caused by the current change from pre-existing repository debt.
  6. Report exactly what ran, what passed, what failed, what was skipped, and the residual risk.
Show full SKILL.md (347 more words)Show less

Deterministic bd Path

For complex QA, do not keep the work as loose shell exploration. Build and execute a deterministic bd plan.

Use the bd path when any of these are true:

  • the request spans multiple QA lanes
  • the work is release-sensitive or compatibility-sensitive
  • multiple failures must be triaged and separated into current vs pre-existing debt
  • the change touches workflows, dependency constraints, or matrix behavior
  • the work needs follow-up tasks, blocker tracking, or phased execution
  • the user asks for a thorough audit or production-readiness assessment

When that happens:

  1. Find an existing scoped bd task or create one.
  2. If the work is too large for one task, create an epic and child tasks by lane or phase.
  3. Claim the active task before substantial work: bd update <id> --claim --json.
  4. Execute the plan deterministically:
    • gather context
    • run the selected checks
    • record exact commands and outcomes in task notes
    • create discovered-from follow-up tasks for unrelated debt
  5. Close the task only after the relevant checks ran or the blockers were explicitly tracked.

Do not hide unrelated repo debt inside the current change. Track it separately.

Repo-Specific Rules

  • Prefer root-level Composer commands for authoritative verification.
  • Use package-level commands only for tight iteration, then return to root verification for shared surfaces.
  • Use act against .github/workflows/php.yml instead of duplicating the matrix in shell scripts.
  • Treat .github/workflows/php.yml as the only matrix source of truth.
  • When dependency constraints or workflow matrix behavior changes, run the targeted local act cell when feasible.
  • If composer qa or composer qa:docs fails because of unrelated existing debt, say so explicitly and file a bd follow-up.
  • Treat composer qa:docs-sites as mandatory for public docs, release-note, generator, or docs workflow changes; generated builds/ content is evidence, never source.
  • For review-style requests, present findings first, ordered by severity, with concrete file references.

Reporting Standard

Your final QA summary should always include:

  • scope and risk model
  • commands actually run
  • passes and failures
  • skipped lanes and why they were skipped
  • whether failures are current-regression or pre-existing debt
  • follow-up bd tasks created for unrelated blockers
  • residual risk after the completed checks

© cognesy, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 2 other files (references) in .codex/skills/instructor-qa of cognesy/instructor-php.

  • SKILL.md
  • agents/openai.yaml
  • references/scenarios.md

Open the folder on GitHubat commit 4a5a54d

Compare with similar skills

Instructor QA next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Instructor QA compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Instructor QA this skillcognesy/instructor-php328—~1.3kAutomated safety check: PassMIT
GreptimeDB Fuzz CI Failure InvestigationGreptimeTeam/greptimedb6.7k—~4.4kAutomated safety check: PassApache-2.0
CI Triagecanton-network/splice118—~1.4kAutomated safety check: PassApache-2.0
Babysit PRZenUml/web-sequence150—~871Automated safety check: PassMIT
Analysing CI Failuresgolemcloud/golem1.5k—~862Automated safety check: PassCustom licence
Nemoclaw Maintainer Classify CI FailureNVIDIA/NemoClaw23k—~806Automated safety check: PassApache-2.0

Similar skills

  • GreptimeDB Fuzz CI Failure Investigation

    GreptimeTeam/greptimedb

    Diagnoses a failed GreptimeDB fuzz CI job by pulling its GitHub Actions logs and fuzz artifacts, then matching the evidence to the local source code.

    6.7k GitHub stars~4.4k tokensUpdated today
    Testing & QAAuto-check passed

  • CI Triage

    canton-network/splice

    Triage a failed splice GitHub Actions job (cn-test-failures ref) into a reproducible evidence packet - fetch job log and artifact, isolate the flagged lines, check the known flake families for…

    118 GitHub stars~1.4k tokensUpdated today
    Testing & QAAuto-check passed

  • Babysit PR

    ZenUml/web-sequence

    Monitor and diagnose GitHub Actions checks on ZenUML web-sequence PRs, fixing code-caused CI failures when appropriate.

    150 GitHub stars~871 tokensUpdated 3 days ago
    Testing & QAAuto-check passed

  • Analysing CI Failures

    golemcloud/golem

    Analysing GitHub Actions CI failures from a run URL. An agent skill from golemcloud/golem.

    1.5k GitHub stars~862 tokensUpdated today
    Testing & QAAuto-check passed

  • Nemoclaw Maintainer Classify CI Failure

    NVIDIA/NemoClaw

    Official

    Classify one failed NemoClaw GitHub Actions job using bounded, redacted logs and optional retained artifacts.

    23k GitHub stars~806 tokensUpdated today
    Testing & QAAuto-check passed

  • Debugging CI Failures

    PostHog/posthog

    Official

    Debugs failing GitHub Actions CI runs for PostHog PRs, commits, and branches, and answers broad CI-health questions ("is CI red?", "is master green today?", "what's broken right now?").

    40k GitHub stars~5.7k tokensUpdated today
    Testing & QAAuto-check passed

More from cognesy/instructor-php

  • Instructor Release

    cognesy/instructor-php

    Prepare and execute a new InstructorPHP version release. An agent skill from cognesy/instructor-php.

    328 GitHub stars~1.7k tokensUpdated 2 days ago
    Auto-check passed

  • Examples QA

    cognesy/instructor-php

    Verify Instructor behavior through the repository's ./examples/ suite in pass, live record, or hermetic replay mode.

    328 GitHub stars~3.2k tokensUpdated 2 days ago
    Auto-check passed

Works with

Categories

Questions about Instructor QA

What does Instructor QA do?

Run multi-dimensional quality assurance for InstructorPHP. An agent skill from cognesy/instructor-php. Instructor QA is an agent skill from cognesy/instructor-php. Run multi-dimensional quality assurance for InstructorPHP.

When should I use Instructor QA?

Instructor QA fits situations like: asked to validate a change; assess production readiness; reproduce CI failures; choose the right verification commands.

How do I install Instructor QA in Claude Code?

Run `npx skills add cognesy/instructor-php --skill instructor-qa -a claude-code`. Or copy the skill folder (.codex/skills/instructor-qa in cognesy/instructor-php) into .claude/skills/instructor-qa in your project. Claude Code loads it when a task matches its description.

How do I install Instructor QA in Codex?

Run `npx skills add cognesy/instructor-php --skill instructor-qa -a codex`. Or copy the skill folder (.codex/skills/instructor-qa in cognesy/instructor-php) into .agents/skills/instructor-qa in your project. Codex loads it when a task matches its description.

Can I use Instructor QA in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add cognesy/instructor-php --skill instructor-qa -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/instructor-qa, .gemini/skills/instructor-qa, .github/skills/instructor-qa and .opencode/skills/instructor-qa in your project.

What does Instructor QA need to run?

Going by SKILL.md and its folder, Instructor QA needs the command-line tools its instructions call (composer).

Does Instructor QA access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Instructor QA safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Instructor QA use?

Instructor QA is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Instructor QA use?

About 1.3k tokens (SKILL.md is roughly 5.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 985 tokens, read only when the agent opens those files.

What are the alternatives to Instructor QA?

Skills that share tags, products or a category with Instructor QA: GreptimeDB Fuzz CI Failure Investigation (GreptimeTeam/greptimedb, 6.7k stars), CI Triage (canton-network/splice, 118 stars), Babysit PR (ZenUml/web-sequence, 150 stars) and Analysing CI Failures (golemcloud/golem, 1.5k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Instructor QA?

cognesy (a GitHub organization) maintains it in cognesy/instructor-php, which has 328 GitHub stars. The repository holds 3 skills in this directory. The repository was last updated on October 6, 2026.

Source: cognesy/instructor-php on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.