CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

file-edit-in-place

Use when the user names a local file and explicitly asks to clean, rewrite, humanize, or remove AI-writing patterns in that file itself, with minimal targeted edits and post-edit verification.

Quality

86%

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

81%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 well-structured, actionable instruction-only skill with an exemplary validation and bounded-repair feedback loop for a mutating operation. Its main weaknesses are mild redundancy between the lens, preconditions, and editing-policy sections, and heavy reliance on external sibling-skill files for the core editing criteria.

DimensionReasoningScore

Conciseness

The body is dense procedural rules with no explanations of concepts Claude already knows, but contains minor duplication — "re-read the changed region" appears both in the implementation lens and Editing Policy step 8, and snapshot/preservation requirements are stated in both the handoff-state list and policy step 1. This matches the efficient-with-trimmable-excess 4 anchor rather than the lean 5.

4 / 5

Actionability

Concrete, executable guidance throughout: a 12-step editing policy, a bounded repair path, exact state markers ("execution_evidence.mutation: executed", "pass.index"/"pass.max"), and explicit stop conditions. Minor gaps — no worked example of a justified vs. unjustified finding, and the core pattern rules are deferred to external files not present in this bundle — keep it below fully copy-paste-ready.

4 / 5

Workflow Clarity

The workflow is clearly sequenced with explicit validation steps (re-read the modified region, VERIFY to preservation-verifier) and a genuine feedback loop: FAIL → repair only blocking errors as the next bounded pass → re-verify once → stop and report if still failing. Pass limits guard this file-mutating operation, matching the top anchor.

5 / 5

Progressive Disclosure

The body is well-sectioned with clearly signaled one-level-deep external references (handoff-contract.md, skill-graph.json, agency-role-lenses.md), but the inlined connection-contract and lens material overlaps content that belongs in those referenced router files. Good structure with minor organization gaps fits the 4 anchor; the 5 anchor would require the split to be cleaner.

4 / 5

Total

17

/

20

Passed

Description

87%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.

A strong description with explicit trigger guidance, concrete named actions, and a clearly bounded niche that separates it from related rewriting and detection skills. The only weakness is slightly incomplete coverage of natural synonym phrasings users might use.

DimensionReasoningScore

Specificity

The description lists several concrete actions — "clean, rewrite, humanize, or remove AI-writing patterns" plus "minimal targeted edits and post-edit verification" — with only minor gaps in coverage, matching the 'several specific actions' anchor rather than the fully comprehensive 5.

4 / 5

Completeness

It explicitly answers both questions: the what ("minimal targeted edits and post-edit verification" applied "in that file itself") and an explicit "Use when..." trigger naming the named file and the explicit request. The 4 anchor (when only partially explicit) does not fit since the trigger clause is fully explicit with concrete phrases.

5 / 5

Trigger Term Quality

Natural user phrases like "clean", "rewrite", "humanize", and "remove AI-writing patterns" give good keyword coverage, though common variations such as "make it sound natural" or "less robotic" are missing, which keeps it below the comprehensive 5 anchor.

4 / 5

Distinctiveness Conflict Risk

It carves a clear niche — in-place mutation of a named local file on explicit request — and distinguishes itself from returned-text rewriting and detector-only audits, so conflict risk with sibling skills is minimal.

5 / 5

Total

18

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository

conorbronsdon/avoid-ai-writing

Path

skills/file-edit-in-place/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.