CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

cleanup-template

Cleanup & restoration plan generator — artifact inventory, persistence removal commands, pre-engagement baseline, post-engagement verification.

Quality

79%

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

Fix and improve this skill with Tessl

tessl review fix ./packages/decepticon/decepticon/skills/standard/soundwave/cleanup-template/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

86%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 tight, well-structured single-file skill: concrete field-level guidance, a real validation checklist, a full output schema, and useful anti-patterns with zero padding. The only notable gaps are the absence of a sample artifact JSON and an explicit fix-and-recheck loop, which keep actionability and workflow clarity at 4.

DimensionReasoningScore

Conciseness

The body is lean and assumes competence: a two-sentence framing ("the anti-foothold roster"), compact tables for kill-chain→artifact mapping and schema fields, a checklist, and terse anti-patterns. Nothing explains concepts Claude already knows and every section earns its tokens, matching the 'lean and efficient' anchor.

5 / 5

Actionability

Guidance is concrete and executable in structure: exact field names and allowed values, the output path `plan/cleanup.json`, the validator `decepticon.core.schemas.CleanupPlan`, and per-artifact `removal_command`/`verifier_command` requirements. It stops short of fully copy-paste-ready output because there is no example CleanupArtifact JSON or sample removal/verifier command, which keeps it at 'mostly executable with minor gaps' rather than 5.

4 / 5

Workflow Clarity

Steps 1–4 are clearly sequenced (map phases → seed artifacts → baseline → completion criteria) and the Validation Checklist plus per-artifact `verifier_command` provide explicit validation checkpoints, so the destructive-operation cap does not apply. It falls just short of 5 because there is no explicit feedback loop (e.g. 'if a checklist item fails, fix and re-check before writing'), matching 'clear sequence with most checkpoints present; minor validation gaps'.

4 / 5

Progressive Disclosure

No bundle files exist (no references/, scripts/, or assets/), and none are needed: the ~90-line body is well-sectioned (When to Use, Workflow, Validation Checklist, Anti-patterns, Output, schema tables) with everything appropriately inlined in one navigable file. This matches the well-organized single-file pattern the rubric rewards for compact self-contained skills.

5 / 5

Total

18

/

20

Passed

Description

66%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 specific, domain-grounded description that names four concrete actions with good trigger keywords. Its main weakness is the missing explicit 'Use when...' trigger clause, which leaves the 'when' only weakly implied and caps completeness at 3.

Suggestions

Append an explicit trigger clause, e.g. "Use when the user asks for a cleanup plan, post-engagement teardown, artifact inventory, or persistence removal steps."

State the concrete deliverable in the description (writing plan/cleanup.json validated against the CleanupPlan schema) so the 'what' is fully concrete.

Add natural trigger variations such as "teardown" and "leave-no-trace" to reduce missed activations.

DimensionReasoningScore

Specificity

The description lists several concrete actions — "artifact inventory", "persistence removal commands", "pre-engagement baseline", "post-engagement verification" — matching the 'several specific actions with minor gaps' anchor. Not a 5 because it never states the concrete deliverable (writing a cleanup plan document / plan/cleanup.json), leaving a small coverage gap.

4 / 5

Completeness

The 'what' is clear (generates a cleanup & restoration plan with inventory, removal commands, baseline, verification), but there is no 'Use when...' clause or equivalent explicit trigger guidance — 'when' is only weakly implied by "post-engagement". Per the rubric guideline, a missing 'Use when...' clause caps completeness at 3; score 4 would require an explicit, if imperfect, 'when' statement.

3 / 5

Trigger Term Quality

Natural domain phrases users would say are present: "cleanup", "restoration plan", "artifact inventory", "persistence removal", "post-engagement". Good keyword coverage but missing common variations users might say such as "teardown", "remove backdoors", or "leave-no-trace", so it fits the 'good coverage, a few natural terms missing' anchor rather than the comprehensive one.

4 / 5

Distinctiveness Conflict Risk

"Cleanup & restoration plan generator" carves a clear niche (engagement teardown / artifact removal) with distinct triggers like "persistence removal" and "pre-engagement baseline". Not a 5 because the bare word "cleanup" overlaps with unrelated skills (code cleanup, file cleanup), creating minor conflict risk with closely related skills.

4 / 5

Total

15

/

20

Passed

Validation

87%

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

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

Total

14

/

16

Passed

Repository

PurpleAILAB/Decepticon

Path

packages/decepticon/decepticon/skills/standard/soundwave/cleanup-template/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.