CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

senpi-qa

QA the omo Senpi adapter (packages/omo-senpi, packages/senpi-task) against the REAL senpi binary in strict isolation, and write every artifact to the one canonical evidence path .omo/evidence/omo-senpi-adapter/<slug>/. The live drivers under packages/omo-senpi/scripts/qa/ create their own isolated SENPI_CODING_AGENT_DIR and ignore the caller's, so the real ~/.senpi/agent is never written. Ships scripts/resolve-evidence-dir.mjs, which is the ONLY sanctioned way to pick an evidence directory: it rejects traversal, separators, absolute paths, and stray roots such as local-ignore/qa-evidence. Use whenever someone changes anything under packages/omo-senpi or packages/senpi-task, or wants to QA, smoke-test, verify, or debug the Senpi adapter, the task/team engine, the DAG, task RPC, or skill delivery. Triggers: senpi qa, qa senpi, senpi-qa, test senpi adapter, verify senpi task, senpi task e2e, senpi team e2e, task dag qa, live senpi driver, senpi evidence path.

Quality

91%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

86%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A lean, highly actionable runbook: exact commands for every case, real validation checkpoints, and well-signaled references verified against the bundle. The only improvements are tightening the duplicated path/resolver statements in the golden rules and making the overall run sequence explicit rather than implied by section order.

DimensionReasoningScore

Conciseness

The body is dense with repo-specific rules and explains nothing Claude already knows, but minor instances could be trimmed: the canonical path and the resolver's rejection rules are each stated twice (golden rules plus the resolver section), and golden-rule sentences carry narrative padding ('The file proves the run on the machine that made it; it is not something the commit carries'). This fits the 4 anchor — efficient with minor over-explanation — rather than the lean 5.

4 / 5

Actionability

Fully executable throughout: a copy-paste resolver invocation with git rev-parse, a router table of exact driver commands per change type (e.g. 'SENPI_BIN="$(command -v senpi)" node packages/omo-senpi/scripts/qa/task-e2e.mjs'), explicit package-gate commands, and an TASK_E2E_OUT_DIR usage example covering the common cases — matching the 5 anchor.

5 / 5

Workflow Clarity

A workable sequence exists (resolve evidence dir, route to a case, run drivers, run the package gate, write the evidence README) with genuine checkpoints ('A SKIP is not a pass', the tracked-evidence audit test failing the build, reporting realSenpiUntouched fields, verifying child PIDs are terminal before the cleanup receipt). It falls short of 5 because the ordering is implicit in section layout rather than explicit, and the placement of the package gate and cleanup relative to the runs has minor gaps.

4 / 5

Progressive Disclosure

Well-organized sections with one-level-deep, clearly signaled references that are real: scripts/resolve-evidence-dir.mjs is verified in the bundle and the README-section rules are delegated to the root AGENTS.md rather than inlined. At this size nothing belongs in a separate file, so navigation is easy — matching the 5 anchor; not 4 because there are no organization gaps to point to.

5 / 5

Total

18

/

20

Passed

Description

95%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A highly specific, well-triggered description that explicitly states both capabilities and use conditions with concrete trigger phrases. Its only weakness is verbosity — mechanism detail about the resolver's validation behavior pads an otherwise strong capability statement.

DimensionReasoningScore

Specificity

Names the domain and multiple concrete actions — QA the adapter against the REAL senpi binary in isolation, write every artifact to the canonical evidence path, resolve the directory via the shipped script — with comprehensive coverage across adapter, task/team engine, DAG, task RPC, and skill delivery. Two sentences of resolver mechanism detail ('it rejects traversal, separators, absolute paths, and stray roots') pad the description beyond the concise comprehensiveness of the 5 anchor.

4 / 5

Completeness

Clearly answers both questions: the 'what' ('QA the omo Senpi adapter ... against the REAL senpi binary in strict isolation, and write every artifact to the one canonical evidence path') and an explicit 'when' ('Use whenever someone changes anything under packages/omo-senpi or packages/senpi-task, or wants to QA, smoke-test, verify, or debug ...'). This mirrors the 5 anchor's structure; not 4 because the when-clause is fully explicit with concrete trigger phrases.

5 / 5

Trigger Term Quality

The explicit trigger list — 'senpi qa, qa senpi, senpi-qa, test senpi adapter, verify senpi task, senpi task e2e, task dag qa, live senpi driver, senpi evidence path' — plus natural verbs like 'smoke-test, verify, or debug' gives comprehensive coverage of natural terms including synonyms, matching the 5 anchor.

5 / 5

Distinctiveness Conflict Risk

Scoped to named packages (packages/omo-senpi, packages/senpi-task) and the senpi binary with senpi-specific triggers, giving it a clear niche with minimal conflict risk against any generic skill.

5 / 5

Total

19

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 1 suspicious

Warning

Total

15

/

16

Passed

Repository

code-yeongyu/oh-my-openagent

Path

.agents/skills/senpi-qa/SKILL.md

Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.