spec-loop-compact-task-file

Compact an active task file without changing meaning. Use when converting a no-subtask task to subtask form, when adding a new subtask after earlier subtasks already contain full section content, when duplicated section content should be compacted before approval seeking, or when a task file has become too large to use safely.

Quality

79%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/spec-loop-compact-task-file/SKILL.md

Quality

Content

80%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 concise, well-structured instruction-only skill with clear rules, allowed/forbidden changes, and stop conditions. Its weaknesses are an implicit (unlisted) workflow sequence and the absence of an explicit post-compaction verification step, plus no concrete before/after example to anchor the action.

Suggestions

Add an explicit verification checkpoint in Stop conditions, e.g. 'After compacting, re-read the result and confirm all preserved items (decisions, dependencies, constraints, review-relevant facts, findings, implementation/test expectations) are still present and unaltered in meaning.'

Number the core workflow as explicit steps (re-read source of truth -> compact per Allowed changes -> verify meaning preserved -> evaluate Stop conditions) so the sequence and checkpoints are visible rather than implicit.

Include a short before/after example of a duplicated section being compacted into one authoritative location to make the action concrete and copy-paste ready.

Dimension	Reasoning	Score
Conciseness	Lean and efficient with no padding or explanation of concepts Claude already knows; every section (Rules, Allowed/Forbidden changes, Stop conditions) earns its place, matching the 'lean and efficient; assumes Claude's competence' anchor.	5 / 5
Actionability	Concrete, specific guidance for an instruction-only skill — explicit lists of what to preserve (decisions, dependencies, constraints, findings), allowed moves, and forbidden actions — but lacks a before/after example showing what a compacted task file looks like, leaving a minor gap.	4 / 5
Workflow Clarity	A sequence is present (re-read source of truth, apply rules, evaluate stop conditions) but it is implicit in prose rather than listed steps, and there is no explicit verification checkpoint that meaning was preserved after compaction — a meaningful gap for an operation that modifies the source-of-truth task file, matching the 'steps present but checkpoints missing or implicit' anchor.	3 / 5
Progressive Disclosure	Well-organized into clear sections with a single clearly-signaled one-level-deep reference (the clarify-task link in Stop conditions); no bundle files exist and none are needed, matching the 'clear overview with well-signaled one-level references; easy navigation' anchor and the simple-skill exception.	5 / 5
	Total	17 / 20 Passed

Description

78%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 that clearly states what the skill does and gives four concrete, natural trigger scenarios. It is concise, third-person, and specific to its niche; the main limitation is narrow action coverage (one compaction action) and minor overlap with sibling spec-loop skills.

Dimension	Reasoning	Score
Specificity	Names the domain ('Compact an active task file without changing meaning') and one core concrete action, but coverage is narrow — a single compaction action applied across several scenarios rather than multiple distinct actions, matching the 'names domain and 1-2 concrete actions, not comprehensive' anchor.	3 / 5
Completeness	Explicitly answers both what ('Compact an active task file without changing meaning') and when (four concrete 'Use when...' trigger clauses), matching the 'clearly and explicitly answers both what AND when with concrete trigger phrases' anchor.	5 / 5
Trigger Term Quality	Multiple natural trigger phrases a spec-loop user would say ('converting a no-subtask task to subtask form', 'duplicated section content should be compacted', 'task file has become too large to use safely'); good coverage with a few synonyms missing, sitting above the 'some relevant keywords' anchor and below fully comprehensive.	4 / 5
Distinctiveness Conflict Risk	Clear niche (task-file compaction) with distinct triggers and minimal conflict risk, but it sits within a family of sibling spec-loop task-file skills (e.g. the referenced clarify-task), giving minor overlap risk with closely related skills rather than fully isolated.	4 / 5
	Total	16 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 1 suspicious	Warning

	Total	15 / 16 Passed

Repository: dpolivaev/spec-loop
Path: skills/spec-loop-compact-task-file/SKILL.md
Commit: 7033338

Reviewed: 6 days 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.