Search

By Chachamaru127

25 skills found.
Search results
#SkillRepositoryStarsUsed inTokensAuto-checkLicenceUpdated
1

Diagnoses failing CI pipelines and tests, deciding first whether the test or the implementation is at fault, and hands hard cases to a dedicated fixer subagent.

Chachamaru127/claude-code-harness3.2k1 repo~1.1kAutomated safety check: NotesMIT5 days ago
2

Hands one implementation task to Cursor Composer in an isolated git worktree, then reviews its diff and cherry-picks the result into the main branch.

Chachamaru127/claude-code-harness3.2k—~4.4kAutomated safety check: NotesMIT5 days ago
3

Renders a single HTML page showing each acceptance criterion as verified or not, with a ship, wait, or reject recommendation for non-engineers.

Chachamaru127/claude-code-harness3.2k—~3.4kAutomated safety check: NotesMIT5 days ago
4

Repeats a long task as a series of scheduled wake-ups, each re-entering with fresh context and calling harness-work for one task per cycle.

Chachamaru127/claude-code-harness3.2k—~2.3kAutomated safety check: NotesMIT5 days ago
5

Creates and maintains Plans.md task plans with a spec delta, updates task markers and syncs plan progress with the implementation.

Chachamaru127/claude-code-harness3.2k—~3.7kAutomated safety check: NotesMIT5 days ago
6

Runs a release for any project that keeps a Keep a Changelog file on GitHub, from version bump to merge, tag and GitHub Release after a single approval.

Chachamaru127/claude-code-harness3.2k—~4.4kAutomated safety check: NotesMIT5 days ago
7

Routes a review request to the right mode and reference file in the claude-code-harness project: code, plan or scope review, a quick closeout, a dual Claude-and-Codex opinion, or a security-only pass.

Chachamaru127/claude-code-harness3.2k—~3.6kAutomated safety check: NotesMIT5 days ago
8

Read-only delegate to cursor-agent (Composer) for questions, investigation, design discussion, and adversarial sanity checks.

Chachamaru127/claude-code-harness3.2k—~1.9kAutomated safety check: NotesMIT5 days ago
9

Run a Cursor Composer review as an advisory second opinion while keeping the primary review verdict on the host brain.

Chachamaru127/claude-code-harness3.2k—~1.1kAutomated safety check: NotesMIT5 days ago
10

Checks and configures Cursor as the implementation backend for Claude Code Harness, at user or project level, without touching shipped defaults.

Chachamaru127/claude-code-harness3.2k—~1.1kAutomated safety check: NotesMIT5 days ago
11

Reads orchestration and judgment logs without writing to them, finds failures that keep recurring, and proposes rule candidates with confidence scores for human review.

Chachamaru127/claude-code-harness3.2k—~603Automated safety check: NotesMIT5 days ago
12

File cleanup and archiving. An agent skill from Chachamaru127/claude-code-harness.

Chachamaru127/claude-code-harness3.2k1 repo~713Automated safety check: NotesMIT5 days ago
13

Manage SSOT, memory, and cross-tool memory search. An agent skill from Chachamaru127/claude-code-harness.

Chachamaru127/claude-code-harness3.2k1 repo~761Automated safety check: NotesMIT5 days ago
14

Starts a background runner that works through ready batches of tasks from Plans.md one cycle at a time via Breezing, with status and stop controls.

Chachamaru127/claude-code-harness3.2k—~2.2kAutomated safety check: NotesMIT5 days ago
15

Generate a Plan Brief HTML for non-engineer vibecoders before implementation starts.

Chachamaru127/claude-code-harness3.2k—~2.2kAutomated safety check: NotesMIT5 days ago
16

Generate a Progress Tracker HTML for non-engineer vibecoders to glance at session progress (cc:WIP / cc:TODO / cc:完了 counts, percentage, elapsed/estimated minutes, cost so far/estimate, drift alerts).

Chachamaru127/claude-code-harness3.2k—~1.5kAutomated safety check: NotesMIT5 days ago
17

HAR: Sync Plans.md with implementation. An agent skill from Chachamaru127/claude-code-harness.

Chachamaru127/claude-code-harness3.2k—~1.6kAutomated safety check: NotesMIT5 days ago
18

HAR: Execute Plans.md tasks from single task to full parallel team run.

Chachamaru127/claude-code-harness3.2k—~6.2kAutomated safety check: NotesMIT5 days ago
19

Detect when the operator corrects the agent's Japanese phrasing mid-conversation (rewrites a sentence, calls out a style problem, says 'this wording is bad, say it like X instead') and draft a…

Chachamaru127/claude-code-harness3.2k—~1.5kAutomated safety check: NotesMIT5 days ago
20

Browser automation through the repo agent-browser CLI. An agent skill from Chachamaru127/claude-code-harness.

Chachamaru127/claude-code-harness3.2k—~1.1kAutomated safety check: NotesMIT5 days ago
21

HAR: Project init, tool setup, agent config, memory setup, skill mirror sync.

Chachamaru127/claude-code-harness3.2k—~1.4kAutomated safety check: NotesMIT5 days ago
22

This skill should be used when the user asks to notify other session, requests a session handoff, says tell other agent, or needs a cross-session message.

Chachamaru127/claude-code-harness3.2k—~453Automated safety check: NotesMIT5 days ago
23

Team execution mode — backward-compatible alias for harness-work with team orchestration.

Chachamaru127/claude-code-harness3.2k—~6.4kAutomated safety check: NotesMIT5 days ago
24

Quality guardrail for Claude/Codex update integration. An agent skill from Chachamaru127/claude-code-harness.

Chachamaru127/claude-code-harness3.2k—~1.6kAutomated safety check: NotesMIT5 days ago
25

Team execution mode (Codex host) — backward-compatible alias for harness-work with backend selection, including opt-in Cursor worker delegation.

Chachamaru127/claude-code-harness3.2k—~5.7kAutomated safety check: NotesMIT5 days ago