capture-progress

Turn ephemeral discussion into durable truth in the right artifact. Use when Joel says "capture this", "note this", "write this down", "make this durable", "put this in the doc", or whenever a conversation conclusion should be preserved in project docs, launch plans, lat.md, ADRs, tasks, or memory.

Quality

76%

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/capture-progress/SKILL.md

Quality

Content

67%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.

The content is a well-structured, actionable instruction skill with a clear sequenced workflow and explicit verification. Its main weakness is redundancy: the destination mapping is repeated across three sections, which adds tokens without adding signal.

Suggestions

Merge the decision tree and "Preferred targets by situation" into a single canonical mapping table; the current three overlapping sections ("What counts as capture", the decision tree, "Preferred targets") restate the same project/repo/system/task split.

Strengthen the Verify step into an explicit feedback loop (e.g., "If lat check or tests fail, fix the artifact and re-run before committing") to lift workflow clarity to the top anchor.

Move the trigger-phrase list out of the body or compress it, since the description already carries the triggers verbatim and the body's "When to use" section largely duplicates them.

Dimension	Reasoning	Score
Conciseness	The body avoids explaining concepts Claude already knows, but the same project/repo/system mapping is restated across "What counts as capture", the five-part decision tree, and "Preferred targets by situation", so it could be consolidated.	3 / 5
Actionability	Concrete destination artifacts (launch-plan.md, AGENTS.md, .brain/*, ADRs), a 7-step workflow, and worked examples give mostly executable guidance; being instruction-only with no code is acceptable, with only minor gaps.	4 / 5
Workflow Clarity	A clearly sequenced 7-step workflow includes an explicit Verify step and a mental read-back checkpoint; the verify is conditional and lacks an explicit fix-and-retry loop, so it falls just short of the top anchor.	4 / 5
Progressive Disclosure	No bundle files exist and the single file is well-organized with clear section headers and no nested references; it is over 50 lines with some redundant sections, so it does not reach the top anchor reserved for a lean overview with well-signaled references.	4 / 5
	Total	15 / 20 Passed

Description

86%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 is strong: it pairs a clear what with explicit, natural trigger phrases and concrete destination artifacts. The main weakness is that the core action is stated abstractly rather than as a set of concrete operations.

Suggestions

Sharpen the 'what' into concrete actions (e.g., 'Identify the canonical artifact, rewrite the wording for clarity, and persist the decision to the right doc or memory') rather than the abstract 'turn ephemeral discussion into durable truth'.

Tighten the trigger list so the most distinctive phrases ("capture this", "make this durable", "put this in the doc") lead, reducing overlap with generic note/memory triggers.

Dimension	Reasoning	Score
Specificity	Names the domain and one transformation action ("Turn ephemeral discussion into durable truth in the right artifact") with concrete destinations, but does not enumerate multiple distinct actions like the top anchor; the core verb is abstract rather than a list of concrete operations.	3 / 5
Completeness	Explicitly answers both what (turn ephemeral discussion into durable truth in the right artifact) and when (Use when Joel says... with concrete trigger phrases), matching the top anchor.	5 / 5
Trigger Term Quality	Comprehensive natural trigger phrases quoted verbatim ("capture this", "note this", "write this down", "make this durable", "put this in the doc") plus situational triggers, covering the phrases a user would actually say.	5 / 5
Distinctiveness Conflict Risk	The capture/durable-truth framing is a fairly distinct niche, but generic triggers like "note this", "write this down", and "save that" create minor overlap risk with memory or note-taking skills.	4 / 5
	Total	17 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: joelhooks/joelclaw
Path: skills/capture-progress/SKILL.md
Commit: 7094ced

Reviewed: 3 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.