Skip to content

netresearch/agent-rules-skill / skills/agent-rules

agent-rules

Flagged

Use when creating or updating AGENTS.md files, .github/copilot-instructions.md, or other AI agent rule files, onboarding AI agents to a project, standardizing agent documentation, or when anyone mentions AGENTS.md, agent rules, project onboarding, or codebase documentation for AI agents.

FileKindSize
AGENTS.mdmarkdown4.0 KB
CLAUDE.mdmarkdown9 B
SKILL.mdskill md5.2 KB
assets/.markdownlint-cli2.jsoncother624 B
assets/example-workflows/validate-agents.ymlconfig2.8 KB
assets/root-thin.mdmarkdown5.7 KB
assets/root-verbose.mdmarkdown5.5 KB
assets/scoped/backend-go.mdmarkdown3.6 KB
assets/scoped/backend-php.mdmarkdown3.0 KB
assets/scoped/backend-python.mdmarkdown2.6 KB
assets/scoped/backend-typescript.mdmarkdown2.8 KB
assets/scoped/claude-code-skill.mdmarkdown3.4 KB
assets/scoped/cli.mdmarkdown2.7 KB
assets/scoped/concourse.mdmarkdown5.2 KB
assets/scoped/ddev.mdmarkdown2.4 KB
assets/scoped/docker.mdmarkdown5.3 KB
assets/scoped/documentation.mdmarkdown3.5 KB
assets/scoped/examples.mdmarkdown3.4 KB
assets/scoped/frontend-typescript.mdmarkdown2.7 KB
assets/scoped/github-actions.mdmarkdown5.2 KB
assets/scoped/gitlab-ci.mdmarkdown4.6 KB
assets/scoped/oro-bundle.mdmarkdown6.5 KB
assets/scoped/oro-project.mdmarkdown5.5 KB
assets/scoped/python-modern.mdmarkdown6.1 KB
assets/scoped/resources.mdmarkdown3.5 KB
assets/scoped/skill-repo.mdmarkdown5.4 KB
assets/scoped/symfony.mdmarkdown5.3 KB
assets/scoped/testing.mdmarkdown3.0 KB
assets/scoped/typo3-docs.mdmarkdown3.6 KB
assets/scoped/typo3-extension.mdmarkdown5.1 KB
assets/scoped/typo3-project.mdmarkdown4.7 KB
assets/scoped/typo3-testing.mdmarkdown3.0 KB
checkpoints.yamlconfig14.4 KB
evals/evals.jsonconfig22.9 KB
references/ai-contribution-guidelines.mdmarkdown2.6 KB
references/ai-tool-compatibility.mdmarkdown8.0 KB
references/directory-coverage.mdmarkdown2.5 KB
references/examples/coding-agent-cli/AGENTS.mdmarkdown2.5 KB
references/examples/coding-agent-cli/go.modmanifest45 B
references/examples/coding-agent-cli/scripts-AGENTS.mdmarkdown10.1 KB
references/examples/express-api-ts/.env.exampleother232 B
references/examples/express-api-ts/AGENTS.mdmarkdown3.1 KB
references/examples/express-api-ts/package.jsonmanifest757 B
references/examples/express-api-ts/pnpm-lock.yamlmanifest101 B
references/examples/express-api-ts/src/AGENTS.mdmarkdown3.1 KB
references/examples/express-api-ts/src/config.tsscript917 B
references/examples/express-api-ts/src/controllers/userController.tsscript2.1 KB
references/examples/express-api-ts/src/index.tsscript671 B
references/examples/express-api-ts/src/middleware/errorHandler.tsscript1.0 KB
references/examples/express-api-ts/src/middleware/requestLogger.tsscript471 B
references/examples/express-api-ts/src/routes/health.tsscript428 B
references/examples/express-api-ts/src/routes/users.tsscript397 B
references/examples/express-api-ts/src/utils/errors.tsscript1.2 KB
references/examples/express-api-ts/src/utils/logger.tsscript441 B
references/examples/express-api-ts/tsconfig.jsonconfig630 B
references/examples/fastapi-app/.env.exampleother348 B
references/examples/fastapi-app/AGENTS.mdmarkdown3.2 KB
references/examples/fastapi-app/pyproject.tomlmanifest1.8 KB
references/examples/fastapi-app/src/AGENTS.mdmarkdown2.9 KB
references/examples/fastapi-app/src/__init__.pyscript58 B
references/examples/fastapi-app/src/config.pyscript1.1 KB
references/examples/fastapi-app/src/main.pyscript1.7 KB
references/examples/fastapi-app/src/models/__init__.pyscript278 B
references/examples/fastapi-app/src/models/item.pyscript1.0 KB
references/examples/fastapi-app/src/models/user.pyscript922 B
references/examples/fastapi-app/src/routes/__init__.pyscript110 B
references/examples/fastapi-app/src/routes/health.pyscript470 B
references/examples/fastapi-app/src/routes/items.pyscript1.9 KB
references/examples/fastapi-app/src/routes/users.pyscript1.7 KB
references/examples/fastapi-app/src/services/__init__.pyscript174 B
references/examples/fastapi-app/src/services/item_service.pyscript2.5 KB
references/examples/fastapi-app/src/services/user_service.pyscript2.1 KB
references/examples/fastapi-app/uv.lockmanifest136 B
references/examples/go-api-with-react-admin/.scopesother93 B
references/examples/go-api-with-react-admin/AGENTS.mdmarkdown3.0 KB
references/examples/go-api-with-react-admin/admin/package.jsonmanifest423 B
references/examples/go-api-with-react-admin/admin/src/App.tsxother101 B
references/examples/go-api-with-react-admin/cmd/api/main.goscript75 B
references/examples/go-api-with-react-admin/go.modmanifest31 B
references/examples/go-api-with-react-admin/main.goscript71 B
references/examples/go-with-internal-web-tsx/.scopesother102 B
references/examples/go-with-internal-web-tsx/AGENTS.mdmarkdown3.1 KB
references/examples/go-with-internal-web-tsx/go.modmanifest34 B
references/examples/go-with-internal-web-tsx/internal/web/AGENTS.mdmarkdown3.1 KB
references/examples/go-with-internal-web-tsx/internal/web/package.jsonmanifest329 B
references/examples/go-with-internal-web-tsx/internal/web/src/App.tsxother57 B
references/examples/go-with-internal-web-tsx/internal/web/src/Button.tsxother63 B
references/examples/go-with-internal-web-tsx/internal/web/src/Footer.tsxother63 B
references/examples/go-with-internal-web-tsx/internal/web/src/Header.tsxother63 B
references/examples/go-with-internal-web-tsx/internal/web/src/Sidebar.tsxother65 B
references/examples/go-with-internal-web-tsx/main.goscript85 B
references/examples/go-with-internal-web-tsx/package-lock.jsonmanifest87 B
references/examples/go-with-internal-web-tsx/package.jsonmanifest221 B
references/examples/ldap-selfservice/AGENTS.mdmarkdown2.5 KB
references/examples/ldap-selfservice/go.modmanifest45 B
references/examples/ldap-selfservice/internal-AGENTS.mdmarkdown10.0 KB
references/examples/ldap-selfservice/internal-web-AGENTS.mdmarkdown12.1 KB
references/examples/php-with-frontend/.scopesother89 B
references/examples/php-with-frontend/AGENTS.mdmarkdown3.1 KB
references/examples/php-with-frontend/composer.jsonconfig185 B
references/examples/php-with-frontend/package.jsonmanifest307 B
references/examples/php-with-frontend/pnpm-lock.yamlmanifest101 B
references/examples/php-with-frontend/src/Controller.phpscript41 B
references/examples/php-with-frontend/web/AGENTS.mdmarkdown3.1 KB
references/examples/php-with-frontend/web/package.jsonmanifest515 B
references/examples/php-with-frontend/web/src/App.tsxother63 B
references/examples/php-with-frontend/web/src/Button.tsxother215 B
references/examples/php-with-frontend/web/src/Footer.tsxother125 B
references/examples/php-with-frontend/web/src/Header.tsxother122 B
references/examples/php-with-frontend/web/src/main.tsxother41 B
references/examples/php-with-frontend/web/tsconfig.jsonconfig280 B
references/examples/pnpm-workspace/AGENTS.mdmarkdown2.6 KB
references/examples/pnpm-workspace/package.jsonmanifest105 B
references/examples/pnpm-workspace/packages/web/package.jsonmanifest187 B
references/examples/pnpm-workspace/packages/web/src/index.tsxother258 B
references/examples/pnpm-workspace/pnpm-lock.yamlmanifest920 B
references/examples/pnpm-workspace/pnpm-workspace.yamlconfig27 B
references/examples/simple-ldap-go/AGENTS.mdmarkdown2.5 KB
references/examples/simple-ldap-go/examples-AGENTS.mdmarkdown1.8 KB
references/examples/simple-ldap-go/go.modmanifest43 B
references/examples/t3x-rte-ckeditor-image/AGENTS.mdmarkdown2.5 KB
references/examples/t3x-rte-ckeditor-image/Classes-AGENTS.mdmarkdown12.0 KB
references/examples/t3x-rte-ckeditor-image/composer.jsonconfig174 B
references/feedback-memory-schema.mdmarkdown6.2 KB
references/fleet-sync-sweep.mdmarkdown4.8 KB
references/git-hooks-setup.mdmarkdown2.5 KB
references/output-structure.mdmarkdown5.4 KB
references/quality-rubric.mdmarkdown6.2 KB
references/scripts-guide.mdmarkdown7.7 KB
references/verification-guide.mdmarkdown9.4 KB
scripts/analyze-git-history.shexecutablescript10.2 KB
scripts/check-freshness.shexecutablescript8.9 KB
scripts/detect-golden-samples.shexecutablescript5.7 KB
scripts/detect-heuristics.shexecutablescript3.2 KB
scripts/detect-project.shexecutablescript19.6 KB
scripts/detect-scopes.shexecutablescript13.4 KB
scripts/detect-utilities.shexecutablescript4.6 KB
scripts/extract-adrs.shexecutablescript6.8 KB
scripts/extract-agent-configs.shexecutablescript9.3 KB
scripts/extract-architecture-rules.shexecutablescript19.9 KB
scripts/extract-ci-commands.shexecutablescript12.5 KB
scripts/extract-ci-rules.shexecutablescript16.1 KB
scripts/extract-commands.shexecutablescript11.9 KB
scripts/extract-documentation.shexecutablescript7.8 KB
scripts/extract-github-rulesets.shexecutablescript3.8 KB
scripts/extract-github-settings.shexecutablescript3.6 KB
scripts/extract-ide-settings.shexecutablescript7.0 KB
scripts/extract-platform-files.shexecutablescript8.0 KB
scripts/extract-quality-configs.shexecutablescript14.9 KB
scripts/generate-agents.shexecutablescript118.2 KB
scripts/generate-file-map.shexecutablescript4.6 KB
scripts/lib/config-root.shexecutablescript5.8 KB
scripts/lib/git.shscript1.2 KB
scripts/lib/summary.shscript11.7 KB
scripts/lib/template.shexecutablescript15.9 KB
scripts/score-agents.shexecutablescript9.8 KB
scripts/tests/test-agents-file-write-boundary.shscript5.8 KB
scripts/tests/test-agents-scan-dependency-trees.shexecutablescript4.5 KB
scripts/tests/test-changelog-rule.shexecutablescript3.4 KB
scripts/tests/test-claude-import-file.shscript3.3 KB
scripts/tests/test-command-allowlist.shexecutablescript4.7 KB
scripts/tests/test-dependency-tree-exclusion.shscript2.5 KB
scripts/tests/test-extract-commands-real-scripts.shexecutablescript4.0 KB
scripts/tests/test-git-history-counts.shexecutablescript3.6 KB
scripts/tests/test-golden-sample-file-names.shexecutablescript2.2 KB
scripts/tests/test-json-manifest.shexecutablescript5.5 KB
scripts/tests/test-last-verified-opt-in.shscript1.6 KB
scripts/tests/test-make-target-lookup.shscript2.5 KB
scripts/tests/test-merge-heuristic.shscript1.8 KB
scripts/tests/test-scope-index-heading.shexecutablescript4.4 KB
scripts/tests/test-scope-index-keeps-existing.shexecutablescript2.5 KB
scripts/tests/test-symlink-write-boundary.shexecutablescript6.3 KB
scripts/tests/test-untrusted-git-config.shscript5.0 KB
scripts/tests/test-verification-sidecar.shscript2.7 KB
scripts/validate-structure.shexecutablescript13.3 KB
scripts/verify-commands.shexecutablescript32.5 KB
scripts/verify-content.shexecutablescript13.2 KB

scripts/score-agents.sh

View on GitHub
#!/usr/bin/env bash
# SPDX-License-Identifier: MIT
# SPDX-FileCopyrightText: Netresearch DTT GmbH
# score-agents.sh - Grade AGENTS.md files with a reproducible quality score.
#
# Aggregates the --json output of the four verifier scripts into a per-file
# letter grade (A-F) on a 0-100 scale, ranked worst-first so you know where to
# spend effort. Reproducible: re-running on an unchanged tree yields the same
# grade (no model call, CI-friendly). One caveat - the Currency axis can shift
# within a day for a file whose "Last updated" date is today, because
# check-freshness.sh uses git's bare-date --since.
#
# Five script-measured axes (max points):
#   Structure 25 | Currency 20 | Content 20 | Commands 15 (root only) | Conciseness 20
# A file's percentage = earned / (sum of applicable axis maxima) * 100.
# Scoped files have no Commands axis; their maxima sum to 85 and normalise to 100.
#
# Grades: A >=90  B >=75  C >=50  D >=30  F <30
#
# A separate, QUALITATIVE LLM overlay (Architecture / Actionability /
# Non-obvious-patterns) is NOT part of this number - it varies run to run. See
# references/quality-rubric.md for how an agent layers that review on top.
set -uo pipefail

SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"

PROJECT_DIR=""
JSON=false
REVIEW_FILE=""

while [[ $# -gt 0 ]]; do
    case $1 in
        --json)
            JSON=true
            shift
            ;;
        --review)
            REVIEW_FILE="${2:-}"
            shift 2
            ;;
        --review=*)
            REVIEW_FILE="${1#*=}"
            shift
            ;;
        --help|-h)
            cat <<EOF
Usage: score-agents.sh [PROJECT_DIR] [OPTIONS]

Grade AGENTS.md files with a reproducible 0-100 quality score (worst-first).

Options:
  --json            Emit the machine-readable scoring document on stdout
  --review FILE     Add a secondary, NON-reproducible "with review" grade from a
                    JSON of agent-judged LLM-axis ratings (see quality-rubric.md):
                    { "PATH": {"architecture":"strong|adequate|weak",
                               "actionability":"...","non_obvious":"..."}, ... }
  --help, -h        Show this help message

Axes: Structure 25 | Currency 20 | Content 20 | Commands 15 (root) | Conciseness 20
Grades: A >=90  B >=75  C >=50  D >=30  F <30

The deterministic score never changes on an unchanged tree. The --review overlay
(Architecture, Actionability, Non-obvious patterns) varies and is shown separately.
EOF
            exit 0
            ;;
        *)
            PROJECT_DIR="$1"
            shift
            ;;
    esac
done

PROJECT_DIR="${PROJECT_DIR:-.}"

if ! command -v jq >/dev/null 2>&1; then
    echo "Error: jq is required" >&2
    exit 2
fi

# Optional LLM-axis ratings for the secondary "with review" grade.
REVIEW_JSON='{}'
if [[ -n "$REVIEW_FILE" ]]; then
    if [[ -f "$REVIEW_FILE" ]] && jq -e . "$REVIEW_FILE" >/dev/null 2>&1; then
        REVIEW_JSON=$(cat "$REVIEW_FILE")
    else
        echo "Error: --review file missing or not valid JSON: $REVIEW_FILE" >&2
        exit 2
    fi
fi

# Run a verifier in --json mode; tolerate its non-zero "issues found" exit and
# its human stderr. Echo '{}' if it produced nothing parseable so jq stays happy.
run_json() {
    local script="$1"
    shift
    local out
    out=$(bash "$SCRIPT_DIR/$script" "$PROJECT_DIR" --json "$@" 2>/dev/null || true)
    if [[ -n "$out" ]] && printf '%s' "$out" | jq -e . >/dev/null 2>&1; then
        printf '%s' "$out"
    else
        echo '{}'
    fi
    return 0
}

STRUCT_JSON=$(run_json validate-structure.sh)
FRESH_JSON=$(run_json check-freshness.sh)
CONTENT_JSON=$(run_json verify-content.sh)
COMMANDS_JSON=$(run_json verify-commands.sh)

# Spine = the files validate-structure reports (it already excludes vendored
# example fixtures). Precompute a path -> line-count map for the Conciseness axis.
mapfile -t SPINE < <(printf '%s' "$STRUCT_JSON" | jq -r '(.files // [])[].path')

# Build the path -> line-count map in a SINGLE jq pass (tab-separated stream)
# rather than spawning jq once per file.
LINES_JSON=$(
    for path in "${SPINE[@]}"; do
        full="$PROJECT_DIR/$path"
        n=0
        [[ -f "$full" ]] && n=$(wc -l < "$full" | tr -d ' ')
        printf '%s\t%s\n' "$path" "$n"
    done | jq -Rs 'split("\n") | map(select(. != "")) | map(split("\t"))
                   | map({key: .[0], value: (.[1]|tonumber)}) | from_entries'
)

# --- Scoring (single jq pass; pure function of its inputs => reproducible) -----
SCORING=$(jq -nc \
    --argjson struct "$STRUCT_JSON" \
    --argjson fresh "$FRESH_JSON" \
    --argjson content "$CONTENT_JSON" \
    --argjson commands "$COMMANDS_JSON" \
    --argjson lines "$LINES_JSON" \
    --argjson review "$REVIEW_JSON" \
    '
    def clamp(max): if . < 0 then 0 elif . > max then max else . end;
    def grade(p): if p>=90 then "A" elif p>=75 then "B" elif p>=50 then "C" elif p>=30 then "D" else "F" end;
    def frac(r): if r=="strong" then 1.0 elif r=="adequate" then 0.6 else 0.2 end;

    ($fresh.files // [] | map({(.path): .}) | add // {}) as $fmap |
    ($commands.summary // {passed:0,skipped:0,failed:0}) as $cmd |
    (($cmd.passed // 0) + ($cmd.failed // 0)) as $cmdTotal |

    [ ($struct.files // [])[] |
      .path as $p | .role as $role |
      (.errors // 0) as $se | (.warnings // 0) as $sw |

      # Structure (25)
      ((25 - $se*5 - $sw*2) | clamp(25)) as $structure |

      # Currency (20)
      ($fmap[$p]) as $fr |
      ( if $fr == null then 8
        elif $fr.status == "fresh" then 20
        elif $fr.status == "unknown" then 8
        else ( ($fr.commits_since // 0) as $c |
               if $c <= 7 then 15 elif $c <= 14 then 11 elif $c <= 30 then 7 else 4 end )
        end ) as $currency |

      # Content (20) - issues attributed to this file
      ( [ ($content.issues // [])[] | select(.file == $p) ] ) as $ci |
      ( [ $ci[] | select(.severity=="ERROR") ] | length ) as $ce |
      ( [ $ci[] | select(.severity=="WARN")  ] | length ) as $cw |
      ((20 - $ce*5 - $cw*2) | clamp(20)) as $content_s |

      # Conciseness (20) - by role, from line count
      ($lines[$p] // 0) as $ln |
      ( if $role == "root"
        then ( if $ln<=50 then 20 elif $ln<=80 then 16 elif $ln<=150 then 10 else 5 end )
        else ( if $ln<=150 then 20 elif $ln<=250 then 15 else 8 end )
        end ) as $concise |

      # Commands (15) - root only, and only if there are verifiable commands
      ( if $role=="root" and $cmdTotal>0
        then { applies:true, score: (($cmd.passed*15/$cmdTotal)|floor) }
        else { applies:false, score:0 }
        end ) as $commands_axis |

      ( 25+20+20+20 + (if $commands_axis.applies then 15 else 0 end) ) as $maxApplicable |
      ( $structure+$currency+$content_s+$concise + $commands_axis.score ) as $earned |
      (($earned*100/$maxApplicable)|round) as $pct |

      # Optional qualitative overlay (non-reproducible): blend agent-judged LLM
      # axes (Architecture 10 / Actionability 8 / Non-obvious 7) into a secondary
      # grade. Only present when --review supplied a rating for this path.
      ($review[$p]) as $rv |
      ( if $rv == null then null
        else (frac($rv.architecture // "weak")*10
            + frac($rv.actionability // "weak")*8
            + frac($rv.non_obvious  // "weak")*7) end ) as $llm |
      ( if $llm == null then null
        else ((($earned + $llm) * 100 / ($maxApplicable + 25)) | round) end ) as $blended |

      { path:$p, role:$role, percent:$pct, grade: grade($pct),
        review: (if $rv == null then null
                 else {ratings:$rv, blended_percent:$blended, blended_grade:grade($blended)} end),
        axes: {
          structure:   {score:$structure,   max:25},
          currency:    {score:$currency,    max:20},
          content:     {score:$content_s,   max:20},
          conciseness: {score:$concise,     max:20},
          commands:    (if $commands_axis.applies then {score:$commands_axis.score, max:15} else {score:null, max:null, note:"n/a (scoped / no verifiable commands)"} end)
        }
      }
    ] | sort_by(.percent) as $files |
    ( [ $files[] | select(.review != null) ] ) as $reviewed |
    { schema:1,
      summary: {
        files: ($files|length),
        average: (if ($files|length)>0 then (([$files[].percent]|add)/($files|length))|round else 0 end),
        grade_counts: ($files | group_by(.grade) | map({(.[0].grade): length}) | add // {}),
        reviewed: ($reviewed|length),
        blended_average: (if ($reviewed|length)>0 then (([$reviewed[].review.blended_percent]|add)/($reviewed|length))|round else null end)
      },
      files: $files
    }
    ')

if [[ "$JSON" = true ]]; then
    printf '%s\n' "$SCORING" | jq .
    exit 0
fi

# --- Human report (rendered from the deterministic scoring document) ----------
printf '%s' "$SCORING" | jq -r '
    "AGENTS.md Quality Report  -  " + (.summary.files|tostring) + " file(s), average "
      + (.summary.average|tostring) + "/100   (worst-first)"
      + (if .summary.blended_average != null then "; with-review avg ~" + (.summary.blended_average|tostring) else "" end),
    "",
    ( .files[] |
      "  " + (.grade) + "  " + ((.percent|tostring)+"/100" | (. + (" " * (8 - (.|length)))))
        + "  " + .path,
      "       structure "  + (.axes.structure.score|tostring)  + "/25"
        + "  currency "    + (.axes.currency.score|tostring)    + "/20"
        + "  content "     + (.axes.content.score|tostring)     + "/20"
        + "  conciseness " + (.axes.conciseness.score|tostring) + "/20"
        + (if .axes.commands.score != null then "  commands " + (.axes.commands.score|tostring) + "/15" else "" end),
      ( if .review != null
        then "       with review: " + .review.blended_grade + " ~" + (.review.blended_percent|tostring)
             + "/100  (non-reproducible)"
        else empty end )
    )
'

echo ""
echo "Headline grades are deterministic (reproducible). Any 'with review' line is a"
echo "qualitative LLM overlay (non-reproducible) - see references/quality-rubric.md."
rea-changelog-updatemorluto/reaPrepare or rewrite REA release changelogs and GitHub release notes from pinned Git history, with verified contributor thanks and Release Please synchronization.Stars: 469kUpdated Claude CodeCodexVerifiedInstall
academy-guideanthropics/skillsStop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching courses, tutorials, and use cases from Claude Academy (academy.claude.com), Anthropic's learning hub. Trigger on: "how do I", "how can I", "getting started with", "what can Claude do", "teach me", "learn to use"; questions about artifacts, projects, skills, plugins, connectors, MCP; requests about rolling Claude out to a team, class, or organization; and any ask for training materials, onboarding content, or learning resources. Use it when the user is learning how to use a feature or product — not when they are mid-task and just want the task done. This skill composes with other skills: after consulting product documentation to answer how a Claude feature works, also check here for a matching course or tutorial — a docs-grounded answer and an Academy recommendation belong together. Only recommend on a strong match; never invent Academy content.Stars: 197kUpdated Claude CodeCodexVerifiedInstall
claude-apianthropics/skillsReference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens). SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file).Stars: 197kUpdated Claude CodeCodexUnverifiedInstall
doc-coauthoringanthropics/skillsGuide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks.Stars: 197kUpdated Claude CodeCodexVerifiedInstall