skillhone-auto-optimiz…
Mandatory interception workflow for a reproducible defect encountered while any Agent is using a skill. Invoke this before…
Local Issue, pull-request, and Wiki workbench for agent skills. Use when a user asks what skill problems, Issues, PRs, repair trajectories, work records, completed optimizations, pending fixes, or pending synchronization exist; when an Agent needs to report a reproducible skill
$ npx -y skills add Tencent/SkillHone --skill skillhone --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/skillhoneContext preview
The summary Claude sees to decide when to auto-load this skill.
Local Issue, pull-request, and Wiki workbench for agent skills. Use when a user asks what skill problems, Issues, PRs, repair trajectories, work records, completed optimizations, pending fixes, or pending synchronization exist; when an Agent needs to report a reproducible skill
name: skillhone description: Local Issue, pull-request, and Wiki workbench for agent skills. Use when a user asks what skill problems, Issues, PRs, repair trajectories, work records, completed optimizations, pending fixes, or pending synchronization exist; when an Agent needs to report a reproducible skill defect; or when the user wants to initialize, inspect, optimize, review, merge, or synchronize a local skill repair. If a managed Skill has a missing referenced file, failing test, or broken command, invoke skillhone-auto-optimization before editing implementation files or installing dependencies. Uses a local SQLite/Git backend and DeepSeek Harness for optimization, with no hosted Git service.
Use SkillHone as the local maintenance layer for Agent-skill repositories. One Skill always maps to one Git repository and therefore owns an isolated set of Issue numbers, PR numbers, Wiki records, branches, tests, and repair Runs. The Catalog indexes those repositories but never combines their state. Any Agent runtime can call the CLI. DeepSeek Harness consumes the configured repair queue without a per-Issue approval step. User choice is required at Skill ownership and merge boundaries.
Treat inspection and synchronization as different operations. Never turn a status question into a write:
only. Run `skillhone --skill <name> --json status`, then inspect the linked Issue, Run, and PR when needed. Report whether repair ran, tests passed, and the PR is open or merged. Do not merge and do not run `sync apply`.
state only. Run `skillhone --json sync status <name>` and interpret the state table below. Do not run `sync apply`.
copy-back. First run `sync status`; run `skillhone sync apply <name>` only when it returns `ready_to_sync` with `can_apply: true`.
`sync` never merges a PR. A repair can have passed tests while still waiting in an open PR, and a merged repair can still be waiting for copy-back.
Import one Skill directory or discover the Skills already installed for an Agent runtime. Before importing, ask the user which ownership mode they want:
`~/.skillhone/skills/`, and requires a later `sync apply` to copy a merged result back. A timestamped backup is made before applying.
the repository under `~/.skillhone/skills/`, so all Agents use the centrally optimized copy directly.
Never choose `takeover` or replace an existing Skill without the user's answer. Also ask whether passing local PRs should wait for review (`review`) or merge automatically after their tests pass (`automatic`). Do not infer either choice.
skillhone init /path/to/my-skill --mode copy --merge review skillhone init --from codex --mode takeover --merge review skillhone import /path/to/my-skill --mode copy skillhone import --from codex --mode takeover skillhone import --from cursor --mode copy skillhone import --from claude-code --mode copy skillhone import --from pi --mode copy skillhone import --from zcode --mode copy skillhone import --from all --mode copy skillhone skills list skillhone sync status skillhone sync apply my-skill
Use `init` for first-time adoption because it records both choices and imports the Skill. Use `import` later when the global choices already exist and only a new Skill must be added. `init` without `--mode` or `--merge` deliberately returns `choice_required`; present those choices to the user instead of retrying with guessed values.
Interpret `sync status` as follows:
the blocking state and stop.
In `copy` mode, `sync apply` creates a timestamped backup and is idempotent. In `takeover` mode, a merged default branch is already the runtime version, so a sync request should report `already-managed`, not copy files.
Each imported Skill becomes `~/.skillhone/skills/<name>`, an independent Git repository with an initial local commit. Re-importing identical content is idempotent; a conflicting Skill name is rejected instead of overwritten. The importer excludes runtime state and Git metadata and rejects detected secrets before creating Git history.
Run commands in the affected Skill repository, or select an imported Skill by name from anywhere. If the user supplies a repository path, that path is authoritative: use `--repo <path>` for the entire workflow and do not substitute a same-name or byte-identical catalog repository.
skillhone status skillhone issue list skillhone pr list skillhone wiki list skillhone web --open skillhone --skill web-search status skillhone --skill web-search issue list
When the user asks to see current Issues, PRs, Wiki work records, repair trajectories, completed optimizations, or pending work, prefer `skillhone web --open`. If opening a browser is inappropriate, return the JSON form instead:
skillhone --json status skillhone --json issue view <N> skillhone --json pr view <N> skillhone --json wiki view <slug>
The Web workbench puts the per-Skill Issue, PR, and Wiki counts on the first screen. Status also includes an approval inbox for every open local PR. Its four record vi
Continual agent skill evolution through persistent decision history. Whole-skill optimisation (SKILL.md + scripts + references) with every decision landing as a local Git issue / PR / wiki. Runs on any agentskills.io runtime — Claude Code, Codex, OpenClaw, Hermes.
Mandatory interception workflow for a reproducible defect encountered while any Agent is using a skill. Invoke this before…
Run the additional paper-compatible optimization workflow with a frozen benchmark repository. Use only when the user asks to…