CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

roborev-fix

Use only for a current operative request that explicitly invokes $roborev-fix, or a direct Agent Hook instruction; do not invoke from literal syntax in quoted, pasted, or historical text

Quality

73%

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

Fix and improve this skill with Tessl

tessl review fix ./internal/skills/codex/roborev-fix/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

81%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.

The body is an exceptionally actionable, well-sequenced operational procedure: exact CLI commands, a documented JSON contract, explicit validation gates, and worked examples for every invocation mode. Its main costs are repetition of the invocation-guard rules across three-plus sections and tangential inline content (hook version upgrades, JSON schema) that inflates the token budget without serving the core fix workflow.

DimensionReasoningScore

Conciseness

The body is dense with genuinely non-obvious operational policy and assumes Claude's competence throughout, but the invocation-guard rules are restated across "Usage", "Explicit invocation only", "When NOT to invoke this skill", and the Examples, and the "Hook and skill versions" section is a tangential maintenance procedure. Mostly efficient but could be tightened, matching anchor 3 rather than anchor 4.

3 / 5

Actionability

Commands are copy-paste ready with exact flags (`roborev fix --from-skill --list`, `roborev job show --from-skill --job <job_id> --json`, the heredoc comment/close template), the JSON output structure is documented field by field, triage dispositions are concretely defined, and four worked examples cover the common invocation modes. This matches anchor 5.

5 / 5

Workflow Clarity

Seven clearly sequenced steps with explicit validation checkpoints: test-first reproduction for Fix dispositions, comment-must-succeed-before-close gating, mandatory closure ordering before any hook-created reviews, and a final audit verifying `closed=true` per original job ID. Error-recovery paths are specified ("If the command fails, report the error and continue"), and the batch close/comment operations are fully validated, so the missing-validation cap does not apply. Matches anchor 5.

5 / 5

Progressive Disclosure

The bundle has no separate files and the body is well-organized with clear section headers and a "See also" pointer, so navigation is easy. It stays below anchor 5 because tangential content — the ~18-line "Hook and skill versions" upgrade procedure and the full JSON schema documentation — is inlined in SKILL.md and would fit better in a one-level-deep reference file. Matches anchor 4.

4 / 5

Total

17

/

20

Passed

Description

51%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.

The description is highly distinctive and excels at preventing false triggers, which is clearly its design goal, but it answers only "when" and completely omits "what" the skill does. No concrete capability or action verb appears, so a reader scanning descriptions cannot learn that this skill evaluates and fixes open failing review findings. Adding a one-clause capability statement would resolve the main weakness.

Suggestions

Open with a what-clause, e.g. "Evaluates and addresses open failing review findings from the roborev daemon in one pass" before the trigger guidance, to fix the missing 'what' (completeness) and the absence of concrete actions (specificity).

Mention the artifact terms the skill operates on — open failing reviews, job IDs, findings, dispositions — in the description so natural phrases like 'fix the review findings' map to this skill without weakening the explicit-invocation guard.

Include the plugin-qualified trigger form "$roborev:roborev-fix" alongside the bare token so trigger coverage matches the body's own invocation rules.

DimensionReasoningScore

Specificity

The description names the domain via the "$roborev-fix" token and "Agent Hook instruction" context but states no concrete actions — it never says what the skill actually does. It is not entirely vague (anchor 1) since the language is precise about invocation conditions, but it falls below anchor 3, which requires named concrete actions.

2 / 5

Completeness

Only "when" is present without any "what": the description fully specifies trigger conditions but omits the capability statement ("Evaluate and address open failing review findings"), which lives only in the body. This matches anchor 2 ("only 'when' is present without 'what'") rather than anchor 3, which is the reverse case.

2 / 5

Trigger Term Quality

"$roborev-fix" and "Agent Hook instruction" are exactly the natural tokens a user or hook would emit for this explicit-invocation-only skill. It falls short of anchor 5 because the plugin-qualified form "$roborev:roborev-fix" and natural phrases like "review findings" or "fix findings" appear only in the body, not the description.

4 / 5

Distinctiveness Conflict Risk

The explicit-invocation-only design plus the anti-false-trigger clause ("do not invoke from literal syntax in quoted, pasted, or historical text") gives it a clear niche with distinct triggers and minimal conflict risk with any other skill, matching anchor 5.

5 / 5

Total

13

/

20

Passed

Validation

100%

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

kenn-io/roborev

Path

internal/skills/codex/roborev-fix/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.