Menu

#264 by GitHub stars

humanlayer/skills

build a repo-local skill and install a matching iterated coding-agent GitHub Actions workflow, prompt, memory file, and reference templates

Claude CodeEngineering

History

Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.

View weekly changes

plugins/build-iterated-agentic-loop/skills/build-iterated-agentic-loop/SKILL.md

Week of Nov 2, 2026 · +0 / −0 lines

Before Network or broad shell → After Network or broad shell

653b6411c1f7 → 4d69d20f6e9b

Compare on GitHub

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Network or broad shell

First observation → 653b6411c1f7

No earlier version was observed for comparison.

Compare on GitHub

plugins/design-control-loop/skills/design-control-loop/SKILL.md

Week of Nov 2, 2026 · +0 / −0 lines

Before Network or broad shell → After Network or broad shell

653b6411c1f7 → 4d69d20f6e9b

Compare on GitHub

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Network or broad shell

First observation → 653b6411c1f7

No earlier version was observed for comparison.

Compare on GitHub

plugins/improve-claude-md/skills/improve-claude-md/SKILL.md

Week of Nov 2, 2026 · +0 / −0 lines

Before Network or broad shell → After Network or broad shell

653b6411c1f7 → 4d69d20f6e9b

Compare on GitHub

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Network or broad shell

First observation → 653b6411c1f7

No earlier version was observed for comparison.

Compare on GitHub

plugins/narrow-react-prop-types/skills/narrow-react-prop-types/SKILL.md

Week of Nov 2, 2026 · +0 / −0 lines

Before Network or broad shell → After Network or broad shell

653b6411c1f7 → 4d69d20f6e9b

Compare on GitHub

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Network or broad shell

First observation → 653b6411c1f7

No earlier version was observed for comparison.

Compare on GitHub

plugins/rpi/skills/rpi/SKILL.md

Week of Nov 2, 2026 · +4 / −0 lines

Before Network or broad shell → After Network or broad shell

653b6411c1f7 → 4d69d20f6e9b

+ 55 ## Review the Document
+ 56 
+ 57 After writing or updating a workflow document, read `$SKILLBASE/references/prose.md` and `$SKILLBASE/references/show-me.md`, then review the document against both. Make it shorter, more visual, and easier for a person to digest: cut words and sections that do not earn their place, replace dense prose with the smallest view that makes the point, and keep each visual beside the short text it supports.
+ 58

Compare on GitHub

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Network or broad shell

First observation → 653b6411c1f7

No earlier version was observed for comparison.

Compare on GitHub

plugins/show-me/skills/show-me/SKILL.md

Week of Nov 2, 2026 · +0 / −0 lines

Before Network or broad shell → After Network or broad shell

653b6411c1f7 → 4d69d20f6e9b

Compare on GitHub

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Network or broad shell

First observation → 653b6411c1f7

No earlier version was observed for comparison.

Compare on GitHub

plugins/visual-pr/skills/visual-pr/SKILL.md

Week of Nov 2, 2026 · +0 / −0 lines

Before Network or broad shell → After Network or broad shell

653b6411c1f7 → 4d69d20f6e9b

Compare on GitHub

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Network or broad shell

First observation → 653b6411c1f7

No earlier version was observed for comparison.

Compare on GitHub

View on GitHubAdd to my skills

Verified commit 4d69d20f6e9b57b4fcf0d501ccfb1be961f0f329

git clone --filter=blob:none --no-checkout https://github.com/humanlayer/skills.git .hotskills/humanlayer-skills && git -C .hotskills/humanlayer-skills checkout --detach 4d69d20f6e9b57b4fcf0d501ccfb1be961f0f329 # Copy each selected skill directory from .hotskills/humanlayer-skills into .claude/skills/<skill-name>/
5.6kGitHub stars
135stars in 7 days
7skills in this repository
10commits in 30 days

Heat

7.2
  • Star growth, last 7 daysAhead of 93% of tracked repositories
  • Star growth, last 24 hoursAhead of 94% of tracked repositories
  • Rank movement, last 7 daysAhead of 57% of tracked repositories
  • Commits, last 30 daysAhead of 77% of tracked repositories
  • Accounts asking about it through MCP, last 7 daysNot available
  • Hot votes this weekAhead of 0% of tracked repositories

Heat never changes the order by stars, and sponsorship never touches it. How heat works

Stars over time

Aug 1, 2026Nov 7, 20265,647

Individual skills in this repository

How it works

build-iterated-agentic-loop

When your agent uses it

build a repo-local skill and install a matching iterated coding-agent GitHub Actions workflow, prompt, memory file, and reference templates

What it loads into context

Frontmatter

38 tokens

Always available to the agent

SKILL.md

3,026 tokens

When the skill is activated

Reference documents

35,198 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

  1. Outputs
  2. Workflow
  3. Reference Files

Scripts executed separately

  • references/agent-iteration.ts

Files

  • ../../../../.claude-plugin/marketplace.jsonasset3,572 bytes
  • ../../.claude-plugin/plugin.jsonasset435 bytes
  • SKILL.mdcore13,553 bytes
  • SKILL.mdcore13,553 bytes
  • SKILL.mdcore13,553 bytes
  • SKILL.mdcore13,553 bytes
  • SKILL.mdcore13,553 bytes
  • references/agent-iteration.tsruns5,896 bytes
  • references/agent-runner-templates.mddoc4,369 bytes
  • references/example-skill.mddoc7,466 bytes
  • references/memory-template.mddoc178 bytes
  • references/prompt-template.mddoc1,456 bytes
  • references/response-template.mddoc2,442 bytes
  • references/skill-template.mddoc1,847 bytes
  • references/workflow-template.ymlasset10,521 bytes
  • ../../../design-control-loop/.claude-plugin/plugin.jsonasset609 bytes
  • ../../../improve-claude-md/.claude-plugin/plugin.jsonasset397 bytes
  • ../../../narrow-react-prop-types/.claude-plugin/plugin.jsonasset377 bytes
  • ../../../rpi/.claude-plugin/plugin.jsonasset625 bytes
  • ../../../rpi/agents/codebase-analyzer.mddoc5,670 bytes
  • ../../../rpi/agents/codebase-locator.mddoc4,834 bytes
  • ../../../rpi/agents/codebase-pattern-finder.mddoc6,950 bytes
  • ../../../rpi/agents/outline-implementer-agent.mddoc4,452 bytes
  • ../../../rpi/agents/web-search-researcher.mddoc5,969 bytes
  • ../../../rpi/agents/web-search-researcher.mddoc5,969 bytes
  • ../../../rpi/agents/web-search-researcher.mddoc5,969 bytes
  • ../../../rpi/skills/rpi/SKILL.mddoc5,358 bytes
  • ../../../rpi/skills/rpi/references/create-design-discussion/process.mddoc4,060 bytes
  • ../../../rpi/skills/rpi/references/create-design-discussion/references/design_discussion_final_answer.mddoc258 bytes
  • ../../../rpi/skills/rpi/references/create-design-discussion/references/design_discussion_final_answer_resolved.mddoc461 bytes
  • ../../../rpi/skills/rpi/references/create-design-discussion/references/design_discussion_template.mddoc1,042 bytes
  • ../../../rpi/skills/rpi/references/create-prd/process.mddoc3,579 bytes
  • ../../../rpi/skills/rpi/references/create-prd/references/prd_final_answer_resolved.mddoc438 bytes
  • ../../../rpi/skills/rpi/references/create-prd/references/prd_template.mddoc853 bytes
  • ../../../rpi/skills/rpi/references/create-research-questions/process.mddoc3,413 bytes
  • ../../../rpi/skills/rpi/references/create-research-questions/references/request_template.mddoc312 bytes
  • ../../../rpi/skills/rpi/references/create-research-questions/references/research_questions_final_answer.mddoc471 bytes
  • ../../../rpi/skills/rpi/references/create-research-questions/references/research_questions_template.mddoc462 bytes
  • ../../../rpi/skills/rpi/references/create-research/process.mddoc5,544 bytes
  • ../../../rpi/skills/rpi/references/create-research/references/research_final_answer.mddoc651 bytes
  • ../../../rpi/skills/rpi/references/create-research/references/research_template.mddoc1,641 bytes
  • ../../../rpi/skills/rpi/references/create-structure-outline/process.mddoc3,297 bytes
  • ../../../rpi/skills/rpi/references/create-structure-outline/references/structure_outline_final_answer.mddoc342 bytes
  • ../../../rpi/skills/rpi/references/create-structure-outline/references/structure_outline_template.mddoc1,074 bytes
  • ../../../rpi/skills/rpi/references/create-tdd/process.mddoc3,637 bytes
  • ../../../rpi/skills/rpi/references/create-tdd/references/tdd_final_answer_resolved.mddoc451 bytes
  • ../../../rpi/skills/rpi/references/create-tdd/references/tdd_template.mddoc776 bytes
  • ../../../rpi/skills/rpi/references/implement-outline/process.mddoc3,009 bytes
  • ../../../rpi/skills/rpi/references/implement-outline/references/implement_outline_final_answer.mddoc504 bytes
  • ../../../rpi/skills/rpi/references/iterate-design-discussion/process.mddoc2,640 bytes
  • ../../../rpi/skills/rpi/references/iterate-design-discussion/references/design_discussion_final_answer.mddoc258 bytes
  • ../../../rpi/skills/rpi/references/iterate-design-discussion/references/design_discussion_final_answer_resolved.mddoc461 bytes
  • ../../../rpi/skills/rpi/references/iterate-design-discussion/references/design_discussion_template.mddoc915 bytes
  • ../../../rpi/skills/rpi/references/iterate-implementation/process.mddoc1,553 bytes
  • ../../../rpi/skills/rpi/references/iterate-implementation/references/iterate_implementation_final_answer.mddoc382 bytes
  • ../../../rpi/skills/rpi/references/iterate-prd/process.mddoc2,484 bytes
  • ../../../rpi/skills/rpi/references/iterate-prd/references/prd_final_answer_resolved.mddoc438 bytes
  • ../../../rpi/skills/rpi/references/iterate-prd/references/prd_template.mddoc853 bytes
  • ../../../rpi/skills/rpi/references/iterate-research-questions/process.mddoc2,530 bytes
  • ../../../rpi/skills/rpi/references/iterate-research-questions/references/research_questions_final_answer.mddoc473 bytes
  • ../../../rpi/skills/rpi/references/iterate-research-questions/references/research_questions_template.mddoc462 bytes
  • ../../../rpi/skills/rpi/references/iterate-research/process.mddoc4,492 bytes
  • ../../../rpi/skills/rpi/references/iterate-research/references/research_final_answer.mddoc710 bytes
  • ../../../rpi/skills/rpi/references/iterate-research/references/research_template.mddoc1,475 bytes
  • ../../../rpi/skills/rpi/references/iterate-structure-outline/process.mddoc2,228 bytes
  • ../../../rpi/skills/rpi/references/iterate-structure-outline/references/structure_outline_final_answer.mddoc344 bytes
  • ../../../rpi/skills/rpi/references/iterate-structure-outline/references/structure_outline_template.mddoc1,074 bytes
  • ../../../rpi/skills/rpi/references/iterate-tdd/process.mddoc2,717 bytes
  • ../../../rpi/skills/rpi/references/iterate-tdd/references/tdd_final_answer_resolved.mddoc451 bytes
  • ../../../rpi/skills/rpi/references/iterate-tdd/references/tdd_template.mddoc776 bytes
  • ../../../rpi/skills/rpi/references/prose.mddoc1,501 bytes
  • ../../../rpi/skills/rpi/references/show-me.mddoc3,297 bytes
  • ../../../rpi/skills/rpi/references/subagents/codebase-analyzer.mddoc5,670 bytes
  • ../../../rpi/skills/rpi/references/subagents/codebase-locator.mddoc4,834 bytes
  • ../../../rpi/skills/rpi/references/subagents/codebase-pattern-finder.mddoc6,950 bytes
  • ../../../rpi/skills/rpi/references/subagents/outline-implementer-agent.mddoc4,452 bytes
  • ../../../rpi/skills/rpi/references/subagents/web-search-researcher.mddoc5,969 bytes
  • ../../../rpi/skills/rpi/references/workflow-choice.mddoc2,596 bytes
  • ../../../rpi/skills/rpi/references/workflow.mddoc3,810 bytes
  • ../../../show-me/.claude-plugin/plugin.jsonasset394 bytes
  • ../../../visual-pr/.claude-plugin/plugin.jsonasset392 bytes
Read SKILL.md

# Build Iterated Agentic Loop

Use this skill when the user wants to turn a repeatable agent task into a repo-local skill plus a GitHub Actions workflow that runs a coding agent on a schedule, manually, or both.

The target shape is an iterated agentic loop: a focused skill defines the agent's judgement, a workflow invokes a coding agent with a repo-specific prompt, an agent-memory file carries standing feedback between runs, and each workflow labels its PRs so only one open PR exists per loop. The `narrow-react-prop-types` skill is the concrete reference pattern.

## Outputs

Create or update these files in the target repo:

- `.claude/skills/<skill-name>/SKILL.md` for the repo-local agent behavior.
- `.github/workflows/agent-<task-name>.yml` for the recurring coding-agent automation.
- `.github/agent-memory/<task-name>.md` for stable feedback and scope constraints.
- Optional references under `.claude/skills/<skill-name>/references/` when the skill needs templates, examples, or long supporting material.
View the complete source on GitHub

Skills included

  • build-iterated-agentic-loop
  • design-control-loop
  • improve-claude-md
  • narrow-react-prop-types
  • rpi
  • show-me
  • visual-pr

Repository facts

License
MIT
Created
Mar 18, 2026
Last pushed
Nov 1, 2026
Forks
193
Open issues
5
Project activity
Active

Rank over the last 12 weeks

Now #264 · best #237 · down 23 in 30 days

  1. #256 from Nov 1 to Nov 2
  2. #258 on Nov 3
  3. #257 on Nov 4
  4. #258 on Nov 5
  5. #261 on Nov 6
  6. #264 since Nov 7
76 earlier periods
  1. #875 on Aug 8
  2. #881 on Aug 9
  3. #912 on Aug 10
  4. #910 on Aug 12
  5. #904 on Aug 13
  6. #880 on Aug 14
  7. #847 on Aug 15
  8. #869 on Aug 16
  9. #871 on Aug 17
  10. #889 on Aug 18
  11. #880 on Aug 19
  12. #871 on Aug 20
  13. #877 on Aug 21
  14. #822 on Aug 22
  15. #873 on Aug 23
  16. #880 on Aug 24
  17. #881 on Aug 25
  18. #850 on Aug 26
  19. #851 on Aug 27
  20. #881 on Aug 28
  21. #798 on Aug 29
  22. #803 on Aug 30
  23. #843 on Aug 31
  24. #859 on Sep 1
  25. #828 on Sep 2
  26. #438 on Sep 3
  27. #366 on Sep 4
  28. #324 on Sep 5
  29. #284 on Sep 6
  30. #279 on Sep 7
  31. #270 on Sep 8
  32. #268 on Sep 9
  33. #267 on Sep 10
  34. #259 on Sep 11
  35. #257 on Sep 12
  36. #258 on Sep 13
  37. #256 on Sep 14
  38. #253 on Sep 15
  39. #250 on Sep 16
  40. #247 on Sep 17
  41. #250 on Sep 18
  42. #245 on Sep 19
  43. #249 on Sep 20
  44. #250 on Sep 21
  45. #249 on Sep 22
  46. #250 from Sep 23 to Sep 24
  47. #248 on Sep 25
  48. #249 on Sep 26
  49. #248 on Sep 27
  50. #250 from Sep 28 to Sep 29
  51. #243 on Sep 30
  52. #245 from Oct 1 to Oct 2
  53. #240 on Oct 3
  54. #238 on Oct 4
  55. #237 on Oct 5
  56. #238 on Oct 6
  57. #242 on Oct 7
  58. #241 on Oct 8
  59. #244 on Oct 9
  60. #240 on Oct 10
  61. #241 on Oct 11
  62. #244 on Oct 12
  63. #246 on Oct 13
  64. #245 from Oct 14 to Oct 15
  65. #243 on Oct 16
  66. #245 on Oct 17
  67. #246 from Oct 18 to Oct 19
  68. #244 on Oct 20
  69. #245 on Oct 21
  70. #246 on Oct 22
  71. #245 on Oct 23
  72. #246 from Oct 24 to Oct 25
  73. #249 on Oct 28
  74. #253 on Oct 29
  75. #254 on Oct 30
  76. #258 on Oct 31

Before you install

Network or broad shell

Automated signals, not a guarantee

Checked Nov 4, 2026

Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.

Show 13 notes
  • plugins/build-iterated-agentic-loop/skills/build-iterated-agentic-loop/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • plugins/build-iterated-agentic-loop/skills/build-iterated-agentic-loop/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • plugins/build-iterated-agentic-loop/skills/build-iterated-agentic-loop/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • plugins/build-iterated-agentic-loop/skills/build-iterated-agentic-loop/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • plugins/rpi/agents/web-search-researcher.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • plugins/rpi/agents/web-search-researcher.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • plugins/design-control-loop/skills/design-control-loop/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • plugins/rpi/agents/web-search-researcher.md:1 Plugin-wide analysis incomplete; see repository notes
  • plugins/narrow-react-prop-types/skills/narrow-react-prop-types/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • plugins/narrow-react-prop-types/skills/narrow-react-prop-types/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • plugins/rpi/agents/web-search-researcher.md:1 Plugin-wide analysis incomplete; see repository notes
  • plugins/rpi/agents/web-search-researcher.md:1 Plugin-wide analysis incomplete; see repository notes
  • plugins/rpi/agents/web-search-researcher.md:1 Plugin-wide analysis incomplete; see repository notes
Show all 80 signals by file

.claude-plugin/marketplace.json

  • Network accessline 1
    {   "$schema": "https://anthropic.com/claude-code/marketplace.schema.json",
  • Network accessline 2
    "$schema": "https://anthropic.com/claude-code/marketplace.schema.json",

plugins/build-iterated-agentic-loop/.claude-plugin/plugin.json

  • Network accessline 7
    "email": "support@humanlayer.dev"   },   "repository": "https://github.com/humanlayer/skills",
  • Network accessline 8
    },   "repository": "https://github.com/humanlayer/skills",   "license": "MIT",
  • Network accessline 9
    "repository": "https://github.com/humanlayer/skills",

plugins/build-iterated-agentic-loop/skills/build-iterated-agentic-loop/SKILL.md

  • Network accessline 96
    - Include a response template as a reference file (e.g., `references/response-template.md` under the skill directory) that defines how the CI agent should format its final output. The skill should instruct the agent to read and follow this
  • Network accessline 98
    - You may refer to https://agentskills.io/specification to understand skill specification.
  • Dangerous shell operationline 170
    yq eval '.name' .github/workflows/agent-<task-name>.yml

plugins/build-iterated-agentic-loop/skills/build-iterated-agentic-loop/references/agent-iteration.ts

  • Executable scriptline 1
    #!/usr/bin/env bun

plugins/build-iterated-agentic-loop/skills/build-iterated-agentic-loop/references/agent-runner-templates.md

  • Access to secretsline 11
    [Credential-related source omitted]
  • Access to secretsline 20
    [Credential-related source omitted]
  • Access to secretsline 47
    [Credential-related source omitted]
  • Access to secretsline 56
    [Credential-related source omitted]
  • Access to secretsline 57
    [Credential-related source omitted]
  • Access to secretsline 75
    [Credential-related source omitted]
  • Access to secretsline 82
    [Credential-related source omitted]
  • Instruction override signalline 86
    --model anthropic/claude-sonnet-4-5 \       --format json \       --dangerously-skip-permissions \
  • Instruction override signalline 87
    --format json \       --dangerously-skip-permissions \       2>&1 | tee /tmp/agent-output.txt
  • Instruction override signalline 88
    --dangerously-skip-permissions \
  • Access to secretsline 92
    [Credential-related source omitted]
  • Access to secretsline 109
    [Credential-related source omitted]
  • Access to secretsline 115
    [Credential-related source omitted]

plugins/build-iterated-agentic-loop/skills/build-iterated-agentic-loop/references/workflow-template.yml

  • Access to secretsline 138
    [Credential-related source omitted]

plugins/design-control-loop/.claude-plugin/plugin.json

  • Network accessline 7
    "email": "support@humanlayer.dev"   },   "repository": "https://github.com/humanlayer/skills",
  • Network accessline 8
    },   "repository": "https://github.com/humanlayer/skills",   "license": "MIT",
  • Network accessline 9
    "repository": "https://github.com/humanlayer/skills",

plugins/design-control-loop/skills/design-control-loop/SKILL.md

  • Network accessline 87
    - Keep one source of truth for each rule; do not repeat the same guidance in the skill, the prompt, and the memory file. - Include a response template (e.g. `references/response-template.md`) defining how the agent formats its final output,
  • Network accessline 89
    - Use `references/skill-template.md` as the skeleton and `references/example-skill.md` as a concrete example. See https://agentskills.io/specification for the skill spec.

plugins/design-control-loop/skills/design-control-loop/references/agent-iteration.ts

  • Executable scriptline 1
    #!/usr/bin/env bun

plugins/design-control-loop/skills/design-control-loop/references/agent-runner-templates.md

  • Access to secretsline 10
    [Credential-related source omitted]
  • Access to secretsline 19
    [Credential-related source omitted]
  • Access to secretsline 28
    [Credential-related source omitted]
  • Access to secretsline 55
    [Credential-related source omitted]
  • Access to secretsline 64
    [Credential-related source omitted]
  • Access to secretsline 65
    [Credential-related source omitted]
  • Access to secretsline 83
    [Credential-related source omitted]
  • Access to secretsline 90
    [Credential-related source omitted]
  • Instruction override signalline 94
    --model anthropic/claude-sonnet-4-5 \       --format json \       --dangerously-skip-permissions \
  • Instruction override signalline 95
    --format json \       --dangerously-skip-permissions \       2>&1 | tee /tmp/agent-output.txt
  • Instruction override signalline 96
    --dangerously-skip-permissions \
  • Access to secretsline 100
    [Credential-related source omitted]
  • Access to secretsline 117
    [Credential-related source omitted]
  • Access to secretsline 123
    [Credential-related source omitted]

plugins/design-control-loop/skills/design-control-loop/references/example-control-loop.md

  • Network accessline 13
    The [`react-doctor`](https://github.com/millionco/react-doctor) CLI scans the app and reports prioritized issues; `doctor.config.ts` configures which rules run and which paths/rules are ignored. It runs locally exactly as it does in CI:

plugins/design-control-loop/skills/design-control-loop/references/workflow-template.yml

  • Access to secretsline 142
    [Credential-related source omitted]
  • Access to secretsline 195
    [Credential-related source omitted]

plugins/improve-claude-md/.claude-plugin/plugin.json

  • Network accessline 7
    "email": "support@humanlayer.dev"   },   "repository": "https://github.com/humanlayer/skills",
  • Network accessline 8
    },   "repository": "https://github.com/humanlayer/skills",   "license": "MIT",
  • Network accessline 9
    "repository": "https://github.com/humanlayer/skills",

plugins/narrow-react-prop-types/.claude-plugin/plugin.json

  • Network accessline 7
    "email": "support@humanlayer.dev"   },   "repository": "https://github.com/humanlayer/skills",
  • Network accessline 8
    },   "repository": "https://github.com/humanlayer/skills",   "license": "MIT",
  • Network accessline 9
    "repository": "https://github.com/humanlayer/skills",

plugins/narrow-react-prop-types/skills/narrow-react-prop-types/references/agent-narrow-component-props.yml

  • Access to secretsline 131
    [Credential-related source omitted]

plugins/rpi/.claude-plugin/plugin.json

  • Network accessline 7
    "email": "support@humanlayer.dev"   },   "repository": "https://github.com/humanlayer/skills",
  • Network accessline 8
    },   "repository": "https://github.com/humanlayer/skills",   "license": "MIT",
  • Network accessline 9
    "repository": "https://github.com/humanlayer/skills",

plugins/rpi/agents/web-search-researcher.md

  • Network accessline 40
    ### For LLMS.txt and sub-links (ends in `.txt` or `.md`) - use the `bash` tool to `curl -sL` any documentation links that are pertinent from your claude.md instructions which end in `llms.txt`
  • Network accessline 41
    - use the `bash` tool to `curl -sL` any documentation links that are pertinent from your claude.md instructions which end in `llms.txt`
  • Network accessline 42
    - read the result and locate any sub-pages that appear to be relevant, and use `curl` to read these pages as well. - `llms.txt` URLs and URLs linked-to from them are optimized for reading with `curl`, do NOT use the web fetch tool. - if you
  • Network accessline 43
    - `llms.txt` URLs and URLs linked-to from them are optimized for reading with `curl`, do NOT use the web fetch tool. - if you know the URL / site for an app (e.g. `https://vite.dev`), you can _always_ try curl-ing `https://<site>/llms.txt`
  • Network accessline 44
    - if you know the URL / site for an app (e.g. `https://vite.dev`), you can _always_ try curl-ing `https://<site>/llms.txt` to see if a `llms.txt` file is available. it may or may not be, but you should always check since it is a VERY valuab
  • Network accessline 45
    - **any URLs which end in `.md` or `.txt` should be fetched with curl rather than web fetch this way!**

plugins/rpi/skills/rpi/references/subagents/web-search-researcher.md

  • Network accessline 40
    ### For LLMS.txt and sub-links (ends in `.txt` or `.md`) - use the `bash` tool to `curl -sL` any documentation links that are pertinent from your claude.md instructions which end in `llms.txt`
  • Network accessline 40
    ### For LLMS.txt and sub-links (ends in `.txt` or `.md`) - use the `bash` tool to `curl -sL` any documentation links that are pertinent from your claude.md instructions which end in `llms.txt`
  • Network accessline 41
    - use the `bash` tool to `curl -sL` any documentation links that are pertinent from your claude.md instructions which end in `llms.txt`
  • Network accessline 41
    - use the `bash` tool to `curl -sL` any documentation links that are pertinent from your claude.md instructions which end in `llms.txt`
  • Network accessline 42
    - read the result and locate any sub-pages that appear to be relevant, and use `curl` to read these pages as well. - `llms.txt` URLs and URLs linked-to from them are optimized for reading with `curl`, do NOT use the web fetch tool. - if you
  • Network accessline 42
    - read the result and locate any sub-pages that appear to be relevant, and use `curl` to read these pages as well. - `llms.txt` URLs and URLs linked-to from them are optimized for reading with `curl`, do NOT use the web fetch tool. - if you
  • Network accessline 43
    - `llms.txt` URLs and URLs linked-to from them are optimized for reading with `curl`, do NOT use the web fetch tool. - if you know the URL / site for an app (e.g. `https://vite.dev`), you can _always_ try curl-ing `https://<site>/llms.txt`
  • Network accessline 43
    - `llms.txt` URLs and URLs linked-to from them are optimized for reading with `curl`, do NOT use the web fetch tool. - if you know the URL / site for an app (e.g. `https://vite.dev`), you can _always_ try curl-ing `https://<site>/llms.txt`
  • Network accessline 44
    - if you know the URL / site for an app (e.g. `https://vite.dev`), you can _always_ try curl-ing `https://<site>/llms.txt` to see if a `llms.txt` file is available. it may or may not be, but you should always check since it is a VERY valuab
  • Network accessline 44
    - if you know the URL / site for an app (e.g. `https://vite.dev`), you can _always_ try curl-ing `https://<site>/llms.txt` to see if a `llms.txt` file is available. it may or may not be, but you should always check since it is a VERY valuab
  • Network accessline 45
    - **any URLs which end in `.md` or `.txt` should be fetched with curl rather than web fetch this way!**
  • Network accessline 45
    - **any URLs which end in `.md` or `.txt` should be fetched with curl rather than web fetch this way!**

plugins/show-me/.claude-plugin/plugin.json

  • Network accessline 7
    "email": "support@humanlayer.dev"   },   "repository": "https://github.com/humanlayer/skills",
  • Network accessline 8
    },   "repository": "https://github.com/humanlayer/skills",   "license": "MIT",
  • Network accessline 9
    "repository": "https://github.com/humanlayer/skills",

plugins/visual-pr/.claude-plugin/plugin.json

  • Network accessline 7
    "email": "support@humanlayer.dev"   },   "repository": "https://github.com/humanlayer/skills",
  • Network accessline 8
    },   "repository": "https://github.com/humanlayer/skills",   "license": "MIT",
  • Network accessline 9
    "repository": "https://github.com/humanlayer/skills",

How the signals fit together

Facts from a static read of the files at the pinned commit. They describe what the code does, not why.

Some files could not be read; the facts below still hold.

Signal confidence: 53 facts

and 3 more

Works with

Agent compatibility, from the files in this repository
AgentStatusEvidenceInstall to
Claude CodeNativeManifest .claude-plugin/marketplace.json.claude/skills/<skill-name>/
CodexCompatibleStandard SKILL.md plugins/build-iterated-agentic-loop/skills/build-iterated-agentic-loop/SKILL.md.agents/skills/<skill-name>/
CursorCompatibleStandard SKILL.md plugins/build-iterated-agentic-loop/skills/build-iterated-agentic-loop/SKILL.md.cursor/skills/<skill-name>/
Gemini CLICompatibleStandard SKILL.md plugins/build-iterated-agentic-loop/skills/build-iterated-agentic-loop/SKILL.md.gemini/skills/<skill-name>/
GitHub CopilotCompatibleStandard SKILL.md plugins/build-iterated-agentic-loop/skills/build-iterated-agentic-loop/SKILL.md.github/skills/<skill-name>/
OpenCodeCompatibleStandard SKILL.md plugins/build-iterated-agentic-loop/skills/build-iterated-agentic-loop/SKILL.md.opencode/skills/<skill-name>/
  • Native The repository ships a manifest, folder or frontmatter field for this agent.
  • Compatible A standard SKILL.md that this agent can read.
  • Unknown No evidence either way.

Derived automatically from paths, manifests and frontmatter. Not tested on each agent.

You might also use

mattpocock/skills

Skills for Real Engineers. Straight from my .agents directory.

317.2kGitHub stars

obra/superpowers

An agentic skills framework & software development methodology that works.

313.8kGitHub stars

NousResearch/hermes-agent

The agent that grows with you

261.3kGitHub stars

multica-ai/andrej-karpathy-skills

Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions,…

230.4kGitHub stars

anthropics/skills

Public repository for Agent Skills

188.3kGitHub stars

DietrichGebert/ponytail

Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.

186.1kGitHub stars

Explore alternatives and comparisons

Add this badge to your README

It updates every night and links to this page.

humanlayer/skills: #264 on hotskills, 5.6k stars

[![humanlayer/skills on hotskills](https://hotskills.dev/badge/humanlayer-skills.svg)](https://hotskills.dev/skill/humanlayer-skills/)