CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

review-pr

Two-axis senior reviewer. Axis 1 (standards, "is it built right?") runs 6 specialized parallel sub-agents (Security, API/CRUD, Pattern enforcement, Simplicity, Reuse/DRY, Test hygiene) producing a severity-based report. Axis 2 (spec & behavior, "is it the right thing?") runs a 7th fresh-context sub-agent producing a behavior-change confirm-list for the human. Axes are never merged. Scoped to the current branch's diff against the default branch.

Quality

62%

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 ./.agents/skills/review-pr/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

52%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 defines a genuinely rigorous workflow — numbered scoping steps, exact git and script commands, explicit output templates, and enumerated fallback paths for every failure mode — and posting to PRs is properly guarded by an ask-first path. But at ~6,500 words it is heavily padded with 250–470-word single paragraphs of coordinator-only trace bookkeeping, and none of the 16 files it references exist in the bundle, leaving the lens protocol and reference structure unexecutable as shipped.

Suggestions

Ship the 16 referenced files (the six lens-*.md files, LENS-RETURN.md, NO-LENS.md, CHECK-TABLE.md, ACCEPTANCE.md, and the six scripts/) or remove the references — as bundled, every link and script invocation is broken, which is the main driver of the low progressive-disclosure score.

Move the trace/spawn bookkeeping (§3's tier-resolution paragraph, §6's relay emit vocabulary) into a reference file the coordinator reads on demand; it is not needed by the lens agents and inflates the always-loaded body past 6,000 words.

Break the 250–470-word single paragraphs into numbered step lists — each currently interleaves 5–10 concerns (tier resolution, Trace-Run lines, spawn.end outcomes, re-resolve fallbacks, raise timing) that a list would separate, improving both conciseness and workflow clarity.

DimensionReasoningScore

Conciseness

At ~6,500 words the body is heavily padded: §3's tier-resolution paragraph alone runs ~470 words in a single block, three other paragraphs run 250–330 words each, and the 'axes are never merged' invariant is restated five times. It never explains concepts Claude already knows (ruling out anchor 1), but the verbosity and duplicated restatements clearly exceed anchor 2's 'noticeably verbose' only in degree, not kind — it sits at the severe end of anchor 2.

2 / 5

Actionability

Concrete, literal commands appear throughout — 'git merge-base origin/<default-branch> HEAD', 'git log --oneline <merge-base>..HEAD', 'sh scripts/trace.sh begin review-pr subject=pr:#<N> || :', 'POLICY_BASE=<base> sh scripts/lens-slice.sh <base> <dir outside the tree>' — plus exact output templates and explicit decision rules. The gap keeping it from 5: the six referenced scripts are not shipped in the bundle, so those invocations cannot run as packaged.

4 / 5

Workflow Clarity

The sequence is explicit (§0 steps 1–7 scope lock through §7 close) with real feedback loops: slicer exit-2/exit-3 fallbacks, spawn outcome=refused/unreachable/fail handling with a re-resolve recipe, verdicts recorded before posting, and the run closed only after raises. Anchor 5 is missed because 300–470-word single paragraphs interleaving many concerns make the otherwise sound sequence hard to follow.

4 / 5

Progressive Disclosure

The design intends good disclosure — lens instructions in per-lens files, one-level-deep clearly-signaled links — but the bundle ships only SKILL.md: all 10 linked markdown files (lens-*.md, LENS-RETURN.md, NO-LENS.md, CHECK-TABLE.md, ACCEPTANCE.md) and all 6 scripts are absent, so every reference is broken, while coordinator-only trace bookkeeping that belongs in a reference file is inlined.

2 / 5

Total

12

/

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 clearly conveys what the skill does — a two-axis review protocol running seven specialized sub-agents that produce a severity report and a human confirm-list — and is reasonably distinct from generic review skills. However, it contains no 'Use when...' trigger guidance and omits the most natural trigger phrases ('pull request', 'PR', 'code review'), favoring internal vocabulary like 'two-axis' and 'confirm-list' that users would not say.

Suggestions

Add an explicit trigger clause naming natural phrases, e.g. 'Use when asked to review a pull request, do a code review, or check a branch's diff before merge' — this alone would lift completeness from 3.

Include the natural keywords users actually say — 'pull request', 'PR', 'code review', 'review my diff' — rather than leading with internal vocabulary such as 'Two-axis', 'Axis 1', and 'confirm-list'.

Open with one plain-language sentence (e.g. 'Reviews a pull request's diff with seven specialized sub-agents and posts severity-ranked findings as PR comments') before introducing the axis taxonomy, which also covers the currently unmentioned PR-comment-posting capability.

DimensionReasoningScore

Specificity

Lists several concrete actions — 'runs 6 specialized parallel sub-agents (Security, API/CRUD, Pattern enforcement, Simplicity, Reuse/DRY, Test hygiene)', 'producing a severity-based report', 'runs a 7th fresh-context sub-agent producing a behavior-change confirm-list', 'Scoped to the current branch's diff against the default branch' — with minor gaps: it omits PR-comment posting (a major function of the skill) and opens on the abstract 'Two-axis senior reviewer'.

4 / 5

Completeness

The 'what' is explicit and detailed, but there is no 'Use when...' clause or equivalent trigger guidance — only the scope limit 'Scoped to the current branch's diff against the default branch', which bounds rather than triggers — so completeness is capped at 3.

3 / 5

Trigger Term Quality

Some relevant keywords exist (reviewer, Security, diff, branch, Test hygiene) but the phrases a user would naturally say — 'pull request', 'PR', 'code review' — never appear, and the lexicon leans on internal jargon ('Two-axis', 'Axis 1', 'fresh-context sub-agent', 'confirm-list').

3 / 5

Distinctiveness Conflict Risk

The two-axis structure, seven named lenses, and severity-report/confirm-list split form a clear niche mostly distinct from a generic review skill; minor overlap risk remains with any plain 'code review' skill since the word 'reviewer' is generic and no trigger boundary is stated.

4 / 5

Total

14

/

20

Passed

Validation

75%

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

Validation — 12 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

metadata_version

'metadata.version' is missing

Warning

relative_links

Relative link issues: 10 possibly missing (ACCEPTANCE.md, CHECK-TABLE.md, LENS-RETURN.md, NO-LENS.md, lens-api-crud.md, +5 more)

Warning

referenced_paths_exist

Referenced path issues: 6 possibly missing (scripts/agents.lib.sh, scripts/behavior-delta.sh, scripts/guards.config.sh, scripts/lens-slice.config.sh, scripts/lens-slice.sh, +1 more)

Warning

Total

12

/

16

Passed

Repository

agranado2k/agentic-sdlc

Path

.agents/skills/review-pr/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.