CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

merge-prs

Consume analyzed PR plans, implement authorized fixes with contributor credit, validate exact candidates, and merge only owner-selected and explicitly authorized groups through the shared gates. Requires prior review evidence; unknown or failing required checks remain HOLD.

Quality

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./config/quality/skill-templates/merge-prs/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

88%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 tightly written, densely prescriptive process skill: every line is an actionable rule, the workflow is clearly sequenced with validation checkpoints and failure feedback at every phase, and jargon is pipeline-specific rather than filler. The main structural weakness is that all policy detail lives inline and depends on external shared files outside the bundle.

DimensionReasoningScore

Conciseness

The ~80-line body is dense imperative directives with zero concept explanation and no padding (e.g., "Verify identity before changing anything and recheck the remote predecessor before every push"). Every token is a rule or constraint, fully assuming Claude's competence.

5 / 5

Actionability

Concrete process guidance with specific paths (`_tasks/pipeline/prs/1-analyzed/`, `2-implementing/`, `3-done/`), named artifacts (`pre_greened`, `DRIFT`, RED-to-GREEN proof), and explicit rules like "Do not run a fallback command after a failed gate to manufacture success." It stops short of anchor 5 because mechanical details (gate commands, how to refresh PR state) are deferred to the shared files and no literal commands are given.

4 / 5

Workflow Clarity

Four numbered phases (reconcile → repair → validate/admit → reconcile outcome) with pervasive explicit validation checkpoints ("recheck the remote predecessor before every push", "Immediately recheck freeze, PR head, base, candidate and protected surfaces. Any movement or retarget invalidates the receipt") and clear failure dispositions (HOLD, skip held items, repair base failures in their own PR). This batch/destructive workflow has strong feedback loops throughout.

5 / 5

Progressive Disclosure

Clear section structure with the five shared references signaled at the top and one level deep. It falls short of anchor 5 because the full policy content is inlined in the ~80-line body rather than split out, and the referenced `../_shared/*.md` files are not present in this bundle, so navigation cannot be fully resolved locally.

4 / 5

Total

18

/

20

Passed

Description

58%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 communicates a specific, well-scoped capability in third person with concrete actions and a distinct niche, but it reads as pipeline-internal policy rather than a skill description for a user. It lacks any "use when" trigger guidance and omits common natural phrases like "pull request", which limits discoverability.

Suggestions

Add an explicit trigger clause such as "Use when the owner asks to merge analyzed/approved pull requests or implement authorized fixes from reviewed PR plans" to satisfy the 'when' half of completeness.

Include natural synonyms users would actually say — "pull requests", "PRs", "merge", "land" — instead of relying solely on internal terms like "exact candidates", "shared gates", and "HOLD".

Briefly unpack the internal jargon (e.g., "analyzed PR plans" → "PRs with completed review plans") so the description is decodable outside the pipeline context.

DimensionReasoningScore

Specificity

Lists several concrete actions spanning the full lifecycle ("Consume analyzed PR plans", "implement authorized fixes with contributor credit", "validate exact candidates", "merge only owner-selected and explicitly authorized groups"), matching anchor 4. Not anchor 5 because "exact candidates", "shared gates", and "HOLD" are internal pipeline jargon rather than plain concrete objects, and outcome/reporting coverage is absent.

4 / 5

Completeness

The "what" is clear and multi-action, but the second sentence states preconditions ("Requires prior review evidence; unknown or failing required checks remain HOLD") rather than a "when to use" trigger; there is no "Use when..." clause or equivalent, which caps completeness at anchor 3.

3 / 5

Trigger Term Quality

Relevant natural keywords are present ("PR", "merge", "fixes", "checks") but common variations and synonyms are missing — "pull request" is never spelled out, and terms like "land", "CI", or "tests" are absent, matching anchor 3 rather than the fuller coverage of anchor 4.

3 / 5

Distinctiveness Conflict Risk

A clear niche — merging pre-analyzed, owner-authorized PR groups through shared gates — is mostly distinct from generic review or git skills. Not anchor 5 because triggering relies on keywords alone (no explicit trigger phrase), leaving minor overlap risk with general "merge/review these PRs" requests.

4 / 5

Total

14

/

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

diegosouzapw/OmniRoute

Path

config/quality/skill-templates/merge-prs/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.