CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

site-review-remediation

Use when asked to review the whole codebase of a website or web app AND fix what is found, end to end. Works on any stack and hosting type (traditional web host, static host/CDN, app platform, containers). Trigger on "review the whole site and fix everything", "full code review and remediation", "audit and fix this website", or when the requested end state is "every fix validated live". NOT for reviewing a single diff/PR (use a code-review skill), NOT for a gap inventory without fixing (use an NFR/gap-audit skill), NOT for visual-only or conversion-only reviews (use a visual or landing-page review skill).

74

Quality

93%

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

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 strong, experienced-sounding operational skill: sequenced phases, hard-won concrete checks, and validation loops around every destructive or batch operation. The single reference file is real and well signaled; the only tightening opportunities are a few rhetorical sentences and a vague in-body pointer to the pitfalls reference.

DimensionReasoningScore

Conciseness

The body is dense with non-obvious operational guidance (proxy-cache keying on the bare URL, CRLF churn via `--ignore-cr-at-eol`, `actions/upload-artifact` dotfile drops, restore mutations in place) and assumes Claude's competence throughout. A few framing sentences could be trimmed — "The review is the cheap part; the value is in shipping the fixes safely and proving them live" and the rationale for splitting areas — which keeps it below the every-token-earns-its-place bar.

4 / 5

Actionability

For an instruction-only skill the guidance is maximally executable: exact commands (`git diff --stat`, `--ignore-cr-at-eol`, `git push --force-with-lease`, `filter-repo`), concrete file conventions (`review-findings.md` with `DONE: <area>` headings, DONE/IN PROGRESS/OPEN/HANDED BACK states), precise validation procedures (expect 400/405 on test endpoints, intercept POST in browser, compare element positions and document height at two widths), and a per-hosting-type decision table.

5 / 5

Workflow Clarity

Five clearly sequenced phases with validation checkpoints at every risky step: findings labeled CONFIRMED/PLAUSIBLE/REFUTED before recording, resumable progress keyed on DONE headings, re-running a builder's tests plus a 2-4 point mutation check, following real CI runs, hitting production directly with cache busting, and a post-deploy CI smoke test with retries. The destructive history-rewrite path has its own full feedback loop (mirror backup, tree-hash check, fresh-clone verification).

5 / 5

Progressive Disclosure

Good structure: a phased overview body with a clearly signaled References section linking the one real bundle file ([pitfalls.md](references/pitfalls.md), which exists) one level deep, with an accurate content description. The inline "(see references)" pointer in Phase 2 triage is indirect and could name/link pitfalls.md directly, and the pitfalls content summarized in the reference entry duplicates body text — minor organization gaps consistent with the 4 anchor.

4 / 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.

An exemplary description: explicit what and when, natural quoted trigger phrases, and strong negative boundaries against neighboring review skills. The only soft spot is that the capability list is a scope statement rather than an enumeration of the distinct operations the skill performs.

DimensionReasoningScore

Specificity

Concrete actions are named — "review the whole codebase of a website or web app AND fix what is found, end to end" and "every fix validated live" — with the scope made precise by enumerated hosting types ("traditional web host, static host/CDN, app platform, containers"). Not a 5 because the what is stated as a scope-plus-goal rather than a comprehensive list of distinct operations (triage, deployment validation, history rewrite live in the body, not the description).

4 / 5

Completeness

Explicitly answers both: what ("review the whole codebase of a website or web app AND fix what is found, end to end") and when ("Use when asked to…", "Trigger on…", plus a requested-end-state condition). It matches the anchor-5 pattern of a clear what followed by concrete when-phrases, and cannot be a 4 since the when is fully explicit, not merely present.

5 / 5

Trigger Term Quality

Explicit quoted trigger phrases users would naturally say — "review the whole site and fix everything", "full code review and remediation", "audit and fix this website", "every fix validated live" — with synonyms covered (review/audit, fix/remediation). Both a "Use when asked to" clause and a "Trigger on" clause give comprehensive natural-phrase coverage.

5 / 5

Distinctiveness Conflict Risk

Three explicit NOT-for clauses steer it away from adjacent skills — "NOT for reviewing a single diff/PR (use a code-review skill), NOT for a gap inventory without fixing…, NOT for visual-only or conversion-only reviews". A clear niche (whole-site review plus remediation with live validation) with minimal conflict risk.

5 / 5

Total

19

/

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

vannifr/agent-skills

Path

skills/site-review-remediation/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.