codebase-alignment

Given a user-provided set of coding standards (either as direct text input or as a link to a file/URL), systematically review the codebase to identify violations, report findings, and optionally remediate them. The model MUST ask the user for the standards — never guess or assume them.

Quality

66%

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/software-engineering/codebase-alignment/SKILL.md

Quality

Content

73%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, actionable skill body: sequenced phases, confirmation gates before destructive edits, a verification checklist, and a real, well-scoped reference file. The two weak spots are repeated restatement of the must-ask-standards constraint and ripgrep commands written with a grep-style --include flag instead of -g, which keeps them from being copy-paste correct.

Suggestions

State the must-ask-standards constraint once (e.g., in Phase 1 or Rules of Engagement) and reference it elsewhere rather than restating it in Mindset, the workflow, and Troubleshooting.

Fix the ripgrep invocations: ripgrep has no --include flag — use `rg -g '*.{js,ts,vue}' '\bvar\b'` (or `rg --glob`) so the examples are executable as written.

Dedupe the standards-to-tooling pointer, which currently appears in both When to Use and When NOT to Use, and consider moving the full report template into references/ to slim the main file.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient — phases, tables, and terse BAD/GOOD pairs — but the core "MUST ask for the standards" constraint is restated roughly six times (frontmatter echo, Mindset, Phase 1, Rules of Engagement, Troubleshooting) and the `standards-to-tooling` pointer appears in both When to Use and When NOT to Use. Fits "mostly efficient but includes some unnecessary explanation or could be tightened"; not 4 because the repetition is more than minor.	3 / 5
Actionability	Concrete, executable guidance dominates: real scan commands ("rg --include '.{js,ts,vue}' '\bvar\b'", "find <source-dir> -name '[A-Z]*'"), a parse-classification table, an exact report template, and verbatim user prompts. Not 5 because the ripgrep examples use a nonexistent `--include` flag (ripgrep's glob flag is `-g`), so the commands are not copy-paste correct as written.	4 / 5
Workflow Clarity	Five clearly sequenced phases with explicit validation checkpoints: "MUST present findings before offering to fix", confirmation gates before destructive edits ("Apply fixes?"), a Troubleshooting table as error-recovery feedback loops, and a final Verification checklist. Matches the top anchor; the batch/destructive-operation cap does not apply because validation and confirmation steps are explicit.	5 / 5
Progressive Disclosure	Well-sectioned ~210-line body with one clearly signaled, one-level-deep reference ([edge-cases.md](references/edge-cases.md), verified to exist) that appropriately offloads edge-case handling. Not 5 because sizable inline content — the full report template and Rules of Engagement WHY/BAD/GOOD blocks — could arguably live in a reference file; not 3 because what is referenced is clearly signaled and well organized.	4 / 5
	Total	16 / 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 states a clear, multi-action "what" with a differentiating must-ask constraint, but it entirely lacks a "Use when..." trigger clause and omits natural synonyms (style guide, conventions, audit) that users would actually say. Adding explicit trigger phrases would lift both completeness and trigger-term quality.

Suggestions

Append an explicit trigger clause, e.g. "Use when the user says 'audit this codebase', 'align with our standards', 'check our conventions', or asks whether the code follows their style guide."

Include the natural synonyms users say — "style guide", "conventions", "audit" — in the description itself rather than only in the body's When to Use section.

Briefly note the skill's report shape (violations grouped by file and convention with paths and line numbers) to make the action coverage more comprehensive.

Dimension	Reasoning	Score
Specificity	Quotes several concrete actions — "systematically review the codebase to identify violations, report findings, and optionally remediate them" — plus two input modes ("direct text input or as a link to a file/URL"), but coverage has minor gaps (no mention of scan tooling, report grouping, or scope). Not 5 because the action list is not comprehensive; not 3 because it lists more than 1-2 concrete actions.	4 / 5
Completeness	The "what" is clear (review codebase against user-provided standards, report violations, optionally remediate), but there is no "Use when..." clause or equivalent explicit trigger guidance — the "when" is only weakly implied by "user-provided set of coding standards". Per the rubric guideline, a missing 'Use when' clause caps completeness at 3; not 2 because the "what" is concrete and detailed.	3 / 5
Trigger Term Quality	"coding standards", "codebase", and "violations" are relevant keywords, but common natural variations users would say — "style guide", "conventions", "audit", "lint" — appear only in the body, not the description. Fits "some relevant keywords but missing common variations or synonyms"; not 4 because several natural terms are missing.	3 / 5
Distinctiveness Conflict Risk	The hard constraint "The model MUST ask the user for the standards — never guess or assume them" carves out a distinct niche (ad-hoc, user-supplied standards vs. automated linting), leaving only minor overlap risk with closely related code-review/lint-setup skills. Not 5 because "review the codebase to identify violations" could still plausibly trigger for generic code-review requests.	4 / 5
	Total	14 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: pantheon-org/tekhne
Path: skills/software-engineering/codebase-alignment/SKILL.md
Commit: a1083f4

Reviewed: 2 hours 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.