log-triage
Extract failing tests, assertion messages, tracebacks, and red gate results from a large run or verify log without reading its full text.
Skill by threecee
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/threecee-log-triage
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/log-triage
What's inside
- Skill name
log-triage- Description
- Extract failing tests, assertion messages, tracebacks, and red gate results from a large run or verify log without reading its full text. Use when a bounded-read hook blocks a read of a log matching the repository's log globs over the configured line threshold, or when the orchestrator must triage a long verify or lane-run log. Names failures, never causes.
- License
- MIT
- Instructions
- 47 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Log Triage
The log-triage command is the bulk reader specialised for factory logs: it
asks the worker chain to list only actionable failures with exact source
line numbers, discarding passing-test noise. The rules live in
`harness/bulk-read-contract.md`; this skill is the invocation.
## Invocation
```sh
{{LOG_TRIAGE_CMD}} <path-to-log>
```
- Only files matching the repository's log globs (`{{LOG_GLOBS}}`, for
example `*-lane.log` and `verify-*.log`) route here from the hook; other
large files route to `bulk-reader`. Invoking this skill by hand on any
large log is fine.
- Output is structured bullets: exact line number, exact test/gate name,
assertion text or traceback line — never a fix or an architecture opinion.
- Same input boundary and exit codes as `bulk-reader` (2 refused, 3 every
worker failed, nothing echoed); `{{ALLOW_EXTERNAL_FLAG}}` under the same
condition.
- Duplicated test names, retries and re-runs inside one log are where line
numbers drift: confirm each listed line with a bounded read before you cite
it in a handback or a ledger entry (contract §3 rule 4, §6).
## When NOT to use this
Don't use it to decide the fix — it names failures, not causes. Root-cause
the listed failures yourself with `skills/systematic-debugging` once you have
the list. A worker bullet that proposes a cause is out of contract; narrow
the question.
## Escape hatch
A targeted read or `sed -n` slice under the threshold always passes without
invoking this skill; `{{SHUNT_ALLOW}}` exempts named paths;
`{{SHUNT_DISABLE}}` disables the hooks for the session when every configured
worker is unavailable (contract §3 rule 5, §5).
## Parameters
`{{LOG_TRIAGE_CMD}}`, `{{LOG_GLOBS}}`, `{{ALLOW_EXTERNAL_FLAG}}`,
`{{SHUNT_ALLOW}}` and `{{SHUNT_DISABLE}}` are bound in the repository's
operations doc from `harness/bulk-read-contract.md` §4.From threecee/software-factory-kit, MIT.
More from threecee/software-factory-kit
- 0.563score
compare-screenshots
threecee
Compare screenshots to judge which image is less wrong, not to match a baseline.
SkillBFreshness: B★ 2Claude Code +9 - 0.563score
refactor-clean
threecee
Refactor toward one clear owner per concept instead of adding sediment.
SkillBFreshness: B★ 2Claude Code +9 - 0.563score
code-review
threecee
Review a current diff for correctness, stale references, ownership, test quality, unnecessary compatibility, and cleanup.
SkillBFreshness: B★ 2Claude Code +9 - 0.559score
brainstorming
threecee
Explore intent and produce an approved design before unbriefed creative implementation.
SkillBFreshness: B★ 2Claude Code +9 - 0.559score
finishing-a-development-branch
threecee
Use after implementation and tests are complete to choose and safely execute merge, pull-request, keep, or discard handling while respecting normal, linked…
SkillBFreshness: B★ 2Claude Code +9 - 0.559score
independent-lane-review
threecee
Run a fresh-context, multi-model adversarial review of a lane before train assembly or on demand.
SkillBFreshness: B★ 2Claude Code +9 - 0.559score
implement-spec
threecee
Implement an approved spec through reviewable passes.
SkillBFreshness: B★ 2Claude Code +9 - 0.559score
audit-choices
threecee
Audit decisions an implementing agent made beyond the brief, without changing code.
SkillBFreshness: B★ 2Claude Code +9 - 0.557score
handback-digest
threecee
Draft one choices-ledger entry per choice in a lane handback, in the ledger's own ELI5 entry format, as the starting point for the orchestrator's…
SkillBFreshness: B★ 2Claude Code +9 - 0.557score
claude
threecee
Use Claude Code as an independent `claude -p` subagent when the user explicitly asks for Claude, wants a second-agent opinion from Claude, or asks to delegate…
SkillBFreshness: B★ 2Claude Code +9 - 0.557score
bulk-reader
threecee
Answer a narrow question over one or more large repository files without reading their raw content into context.
SkillBFreshness: B★ 2Claude Code +9
Signals
- Stars
- 2
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Sep 6, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/threecee/software-factory-kit
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from threecee
- 0.563score
compare-screenshots
threecee
Compare screenshots to judge which image is less wrong, not to match a baseline.
SkillBFreshness: B★ 2Claude Code +9 - 0.563score
refactor-clean
threecee
Refactor toward one clear owner per concept instead of adding sediment.
SkillBFreshness: B★ 2Claude Code +9 - 0.563score
code-review
threecee
Review a current diff for correctness, stale references, ownership, test quality, unnecessary compatibility, and cleanup.
SkillBFreshness: B★ 2Claude Code +9 - 0.559score
brainstorming
threecee
Explore intent and produce an approved design before unbriefed creative implementation.
SkillBFreshness: B★ 2Claude Code +9 - 0.559score
finishing-a-development-branch
threecee
Use after implementation and tests are complete to choose and safely execute merge, pull-request, keep, or discard handling while respecting normal, linked…
SkillBFreshness: B★ 2Claude Code +9 - 0.559score
independent-lane-review
threecee
Run a fresh-context, multi-model adversarial review of a lane before train assembly or on demand.
SkillBFreshness: B★ 2Claude Code +9
Cite this page
log-triage skill. Agent Mart. https://agentmart.dev/skills/threecee-log-triage (last updated 2026-10-24)