Skip to content
Back to search

skill-optimizer

Agent Skills lifecycle toolkit: mine repeated coding-agent workflows, audit and personalize skills, and generalize personal skills for public release.

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/hqhq1025--skill-optimizer/badge.svg)](/listings/hqhq1025--skill-optimizer)

HTML

<a href="/listings/hqhq1025--skill-optimizer"><img src="/api/listings/hqhq1025--skill-optimizer/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

Copy the command below into your agent's chat:

Claude Code

Install the skills from https://github.com/hqhq1025/skill-optimizer

Codex

Install the skills from https://github.com/hqhq1025/skill-optimizer into ~/.codex/skills/

Other Agent Skills-compatible agents

Install the skills from https://github.com/hqhq1025/skill-optimizer into ~/.agents/skills/

Manual install:

git clone https://github.com/hqhq1025/skill-optimizer.git /tmp/skill-optimizer
mkdir -p ~/.agents/skills
cp -r /tmp/skill-optimizer/skills/skill-miner ~/.agents/skills/
cp -r /tmp/skill-optimizer/skills/skill-personalizer ~/.agents/skills/
cp -r /tmp/skill-optimizer/skills/skill-generalizer ~/.agents/skills/
rm -rf /tmp/skill-optimizer

For Codex-only installs, use `~/.codex/skills/`:

git clone https://github.com/hqhq1025/skill-optimizer.git /tmp/skill-optimizer
mkdir -p ~/.codex/skills
cp -r /tmp/skill-optimizer/skills/skill-generalizer ~/.codex/skills/
cp -r /tmp/skill-optimizer/skills/skill-miner ~/.codex/skills/
cp -r /tmp/skill-optimizer/skills/skill-personalizer ~/.codex/skills/
rm -rf /tmp/skill-optimizer

For Claude Code-only installs, use `~/.claude/skills/`.

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 165 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. # Skill Optimizer
  2. [中文版](./README.zh-CN.md)
  3. Three Agent Skills for turning coding-agent work into better `SKILL.md` files:
  4. - **skill-miner** — mine coding-agent history, archives, memories, and repeated work to surface skill-worthy workflows with evidence.
  5. - **skill-personalizer** — audit and adapt newly created, downloaded, forked, or community skills to one user's own tools, habits, directories, and session history.
  6. - **skill-generalizer** — turn local, private, personal skills into publishable skills for GitHub, marketplaces, teams, or public sharing.
  7. Current release: **v2.0.0**. This is a major redesign from the original single-skill optimizer.
  8. Project site: https://hqhq1025.github.io/skill-optimizer/
  9. The split is intentional. Generating, personalizing, and publishing skills are different jobs:
  10. | Goal | Skill | Optimization Direction |
  11. | --- | --- | --- |
  12. | Mine repeated workflows | `skill-miner` | Scan real agent usage, cluster repeated workflows, and draft evidence-backed candidate skills. |
  13. | Fit inward | `skill-personalizer` | Preserve the original optimizer's audit checks, then add local defaults, user phrasing, preferred tools, verification habits, and workflow shortcuts. |
  14. | Publish outward | `skill-generalizer` | Remove private context, generalize examples, make install and README claims portable. |
  15. See [Research Background](./docs/research-background.md) for related agent-skill ecosystems, comparable projects, and papers that motivate session mining, skill libraries, trigger auditing, progressive disclosure, and lifecycle governance.
  16. ## Installation
  17. Copy the command below into your agent's chat:
  18. ### Claude Code
  19. ```text
  20. Install the skills from https://github.com/hqhq1025/skill-optimizer
  21. ```
  22. ### Codex
  23. ```text
  24. Install the skills from https://github.com/hqhq1025/skill-optimizer into ~/.codex/skills/
  25. ```
  26. ### Other Agent Skills-compatible agents
  27. ```text
  28. Install the skills from https://github.com/hqhq1025/skill-optimizer into ~/.agents/skills/
  29. ```
  30. Manual install:
  31. ```bash
  32. git clone https://github.com/hqhq1025/skill-optimizer.git /tmp/skill-optimizer
  33. mkdir -p ~/.agents/skills
  34. cp -r /tmp/skill-optimizer/skills/skill-miner ~/.agents/skills/
  35. cp -r /tmp/skill-optimizer/skills/skill-personalizer ~/.agents/skills/
  36. cp -r /tmp/skill-optimizer/skills/skill-generalizer ~/.agents/skills/
  37. rm -rf /tmp/skill-optimizer
  38. ```
  39. For Codex-only installs, use `~/.codex/skills/`:
  40. ```bash
  41. git clone https://github.com/hqhq1025/skill-optimizer.git /tmp/skill-optimizer
  42. mkdir -p ~/.codex/skills
  43. cp -r /tmp/skill-optimizer/skills/skill-generalizer ~/.codex/skills/
  44. cp -r /tmp/skill-optimizer/skills/skill-miner ~/.codex/skills/
  45. cp -r /tmp/skill-optimizer/skills/skill-personalizer ~/.codex/skills/
  46. rm -rf /tmp/skill-optimizer
  47. ```
  48. For Claude Code-only installs, use `~/.claude/skills/`.
  49. ## Platform Support
  50. | Agent | Support level | Recommended path |
  51. | --- | --- | --- |
  52. | Codex | Native Agent Skills, plus optional plugin metadata. | `~/.codex/skills/` or `.agents/skills/` |
  53. | Claude Code | Native skills in personal, project, and plugin scopes. | `~/.claude/skills/` or `.claude/skills/` |
  54. | Cursor | Native Agent Skills and rules/commands; skills are discoverable by Agent. | `.agents/skills/`, `.cursor/skills/`, or global skills |
  55. | OpenCode | Native `skill` tool and repo/home skill discovery. | `.agents/skills/`, `.opencode/skills/`, or `~/.config/opencode/skills/` |
  56. | Gemini CLI / Google agents | Agent Skills open format is documented by Google; `GEMINI.md` remains the always-on context mechanism. | `.agents/skills/` or installer-managed skills |
  57. The safest public layout is `skills/<name>/SKILL.md` in the repo plus install instructions that copy into `.agents/skills/` or the target agent's native skill directory.
  58. ## Usage
  59. Ask for the direction you want:
  60. ```text
  61. Mine my coding-agent history and find repeated workflows that should become skills.
  62. ```
  63. ```text
  64. Audit and tune my installed skills; tell me which ones are undertriggering, too noisy, or too generic.
  65. ```
  66. ```text
  67. Turn this local skill into a public GitHub-ready skill.
  68. ```
  69. ```text
  70. I downloaded this skill. Tune it to my local workflow and usage habits.
  71. ```
  72. ```text
  73. This skill does not trigger when I say things naturally. Personalize it for me.
  74. ```
  75. ## What Each Skill Does
  76. ### skill-miner
  77. - coding-agent session history, memory summaries, repo notes, repeated scripts, and project folders
  78. - recurring user intents, shorthand, tool chains, artifacts, and verification patterns
  79. - candidates that are repeated and non-obvious enough to become skills
  80. - whether a candidate should stay personal, be generalized for publication, or be skipped
  81. - includes `scripts/scan_sessions.py` for a deterministic first-pass scan of Codex, Claude Code, Gemini/Antigravity task files, and exported transcripts from other agents
  82. - includes archived Codex sessions and rollout summaries by default, with flags to disable archive/summary sources
  83. Example:
  84. ```bash
  85. python3 skills/skill-miner/scripts/scan_sessions.py --days 30 --limit 300 --min-count 3
  86. python3 skills/skill-miner/scripts/scan_sessions.py --export ~/Downloads/cursor-chat-export.json
  87. python3 skills/skill-miner/scripts/scan_sessions.py --patterns ./my-patterns.json
  88. python3 skills/skill-miner/scripts/scan_sessions.py --no-include-archives --no-include-summaries
  89. ```
  90. ### skill-generalizer
  91. - private paths, hosts, credentials, account names, transcript quotes, and internal repo facts
  92. - public portability of commands, examples, README claims, and install instructions
  93. - frontmatter that describes when to use the skill rather than the workflow
  94. - packaging structure for public distribution
  95. ### skill-personalizer
  96. - local installed copies and nearby project instructions
  97. - real user phrasing and recurring task patterns
  98. - preferred CLIs, MCP tools, paths, aliases, and verification commands
  99. - undertrigger, overtrigger, and unnecessary-question friction
  100. - original optimizer-style audit checks: trigger fit, user reaction, workflow completion, static quality, conflicts, environment consistency, token economics, and P0/P1/P2 fixes
  101. ## Compatibility
  102. Works with agents that support the Agent Skills folder convention:
  103. - Claude Code
  104. - Codex
  105. - Cursor
  106. - OpenCode
  107. - Gemini CLI
  108. ## Research Background
  109. This project is informed by Agent Skills ecosystem work and LLM-agent research on externalized memory, skill libraries, retrieval/routing, and long-context behavior. See [docs/research-background.md](./docs/research-background.md).
  110. ## AI And Search Visibility
  111. - Project site: https://hqhq1025.github.io/skill-optimizer/
  112. - LLM summary: [llms.txt](./llms.txt)
  113. - Full LLM context: [llms-full.txt](./llms-full.txt)
  114. - Structured metadata: [repo-metadata.json](./repo-metadata.json)
  115. ## License
  116. MIT

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.