spec-loop-assess-pull-request

Optional skill. Reconstruct a human-review-preparation file from an existing pull request, merge request, branch diff, or commit range in a repository the user trusts. Use when the user wants retrospective understanding of already-implemented changes, AI-side assessment and recommendations, and an optional provider-specific sharing variant written to a local file when needed.

Quality

75%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/spec-loop-assess-pull-request/SKILL.md

Quality

Content

50%

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

The body is well-organized and appropriately delegates detail to referenced files, but the core referenced file (review-guidance.md) is missing from the bundle and the inline guidance stays high-level. Some redundancy and absent validation checkpoints keep it mid-range.

Suggestions

Add review-guidance.md (and confirm the ../spec-loop-plan-task/* paths resolve) so the primary detail reference is not a dead end.

Include a minimal inline review-artifact skeleton or section checklist so the skill is actionable before consulting the external file.

Remove the duplicated "optional / not required" and "PLAN -> EXECUTION gate" statements to tighten the body.

Dimension	Reasoning	Score
Conciseness	Mostly lean with no concept over-explanation, but repeats the "optional / not required for the core Spec Loop planning workflow" point and the "PLAN -> EXECUTION gate" caveat across the intro and before-work list.	2 / 3
Actionability	Names concrete read-only tools (`gh`, `glab`) and a clear reconstruct-then-assess directive, but the actual review structure and template are fully delegated to review-guidance.md rather than given inline.	2 / 3
Workflow Clarity	A sequenced before-work list and a stop-and-ask guardrail exist, but there are no validation checkpoints between reconstruct, assess, and recommend steps.	2 / 3
Progressive Disclosure	References are clearly labeled and intended one level deep, but the primary detail file review-guidance.md is referenced twice and is not present in the bundle, and several references point to a sibling skill outside the bundle.	2 / 3
	Total	8 / 12 Passed

Description

100%

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 third-person, concrete, and includes an explicit "Use when..." trigger covering both capability and triggering context. Trigger terms map naturally to user phrasing and the niche is distinct.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — "Reconstruct a human-review-preparation file", "AI-side assessment and recommendations", and "provider-specific sharing variant written to a local file" — matching the multiple-specific-actions anchor.	3 / 3
Completeness	Explicitly answers both what (reconstruct review file, assess, recommend, optional sharing variant) and when via a clear "Use when the user wants..." clause.	3 / 3
Trigger Term Quality	Natural trigger terms a user would say are well covered — "pull request, merge request, branch diff, or commit range" — alongside explicit review-oriented phrasing.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear niche (retrospective review of already-implemented changes via trusted repos) with distinct triggers unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 Passed

Validation

93%

Warnings & errors only

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

Criteria	Description	Result
relative_links	Relative link issues: 2 missing, 3 suspicious	Warning

	Total	15 / 16 Passed

Repository: dpolivaev/spec-loop
Path: skills/spec-loop-assess-pull-request/SKILL.md
Commit: 741f932

Reviewed: 4 days ago

Table of Contents

Discovery Implementation Validation

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.