commitment-triage

Recognize obligations in conversation, extract signals with immediacy and expiration, create and manage commitments in the workspace.

Quality

66%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

tessl review fix ./skills/commitment-triage/SKILL.md

Quality

Content

72%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The skill body is highly actionable with well-sequenced, validated workflows across its four modes. Its main weakness is progressive disclosure: schema detail lives inline and the only referenced doc is external to the bundle.

Suggestions

Add a bundled references/ file for the signal/commitment schema and link to it one level deep, rather than pointing only at the external projects/commitments/README.md.

Tighten the repeated trigger-example lists (Modes A passive signals) by consolidating them once, since the activation frontmatter already enumerates the keywords.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean and instruction-focused, but the repeated example trigger lists and some restated immediacy rules add tokens that could be tightened without losing clarity.	2 / 3
Actionability	Each mode gives concrete, executable steps with exact memory_* tool calls, target paths, and copy-ready frontmatter templates — fully actionable rather than abstract.	3 / 3
Workflow Clarity	Modes A–D are clearly sequenced with explicit validation checkpoints (duplicate check before write, confirm only after write succeeds, read-before-resolve matching), giving strong feedback loops for the batch/destructive resolution path.	3 / 3
Progressive Disclosure	No bundle files exist, and the body points to an external README ("Read projects/commitments/README.md for the full schema") that is not part of the skill bundle, leaving schema detail inline rather than split into a one-level-deep reference.	2 / 3
	Total	10 / 12 Passed

Description

60%

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 specific about capabilities but stops short of giving Claude explicit usage triggers, capping completeness. Trigger-term coverage relies on domain nouns rather than the natural user phrasings documented in the body.

Suggestions

Add an explicit 'Use when...' clause naming natural triggers (e.g. 'Use when the user says they need to do something, mentions a deadline, or asks to track a commitment').

Weave in concrete user phrasings like 'I need to', 'track this', or 'due Friday' so the description matches the activation keywords.

Dimension	Reasoning	Score
Specificity	The description names multiple concrete actions — "Recognize obligations", "extract signals with immediacy and expiration", "create and manage commitments" — going beyond a vague domain label.	3 / 3
Completeness	It answers "what" clearly but lacks an explicit "Use when..." / "when should Claude use it" clause, which the guidelines say caps completeness at 2.	2 / 3
Trigger Term Quality	It surfaces domain words (obligations, commitments, signals) but omits the natural phrasings a user would actually say (e.g. "I need to", "track this", "due Friday") that are listed in the body's activation block.	2 / 3
Distinctiveness Conflict Risk	The commitment-tracking niche is reasonably specific, but without explicit trigger phrasing the description could overlap with general task-management or note-taking skills.	2 / 3
	Total	9 / 12 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: nearai/ironclaw
Path: skills/commitment-triage/SKILL.md
Commit: b60038b

Reviewed: 2 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.