commitment-setup

One-time setup for the commitments tracking system. Creates workspace structure, schema docs, and installs triage and digest missions. Excluded from activation once `projects/commitments/README.md` exists in the workspace (the file this skill writes as its first step).

Quality

72%

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/commitment-setup/SKILL.md

Quality

Content

77%

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

The body is highly actionable with concrete tool calls and a well-sequenced, checkpoint-guarded workflow, but it is token-heavy due to a large inline schema and makes no use of bundle/reference files to split that content out. Externalizing the schema or trimming editorial prose would improve conciseness and progressive disclosure.

Suggestions

Move the full README schema (Steps 3-4 content) into a reference file (e.g. references/schema-template.md) that the skill reads and writes verbatim, reducing inline weight and enabling one-level-deep progressive disclosure.

Trim editorial commentary inside the embedded README (e.g. 'This reframes decisions — there is no excuse for shortcuts') unless it is essential to the artifact, to tighten conciseness.

If the schema must stay inline, add a brief 'What this creates' overview near the top pointing to the major sections, so the large artifact is easier to navigate.

Dimension	Reasoning	Score
Conciseness	The step instructions are lean and assume Claude's competence, but the body embeds a ~150-line README schema inline plus light editorializing ('This reframes decisions — when AI makes completeness cheap, there is no excuse for shortcuts.'); not a 3 because the large inline artifact could be tightened or externalized, and not a 1 because it avoids explaining general concepts Claude already knows.	2 / 3
Actionability	Every step gives copy-paste-ready tool invocations — memory_write with explicit target paths and content, mission_create with full goal text and cron cadence, and exact user-facing quotes; matches the fully-executable anchor and is not a 2 because no step relies on pseudocode or vague direction.	3 / 3
Workflow Clarity	Eight clearly sequenced steps with explicit guard checkpoints — Step 1 halts if README already exists unless the user confirms, and Step 5 checks mission_list before creating duplicates; matches the clear-sequence-with-validation anchor and is not a 2 because checkpoints are explicit rather than implicit.	3 / 3
Progressive Disclosure	Sections are well-organized (Steps 1-8, structured README), but everything is monolithically inline with no external references and the ~150-line schema could plausibly be a separate reference file; not a 3 because the under-50-lines simple-skill exception does not apply, and not a 1 because there are no deeply nested references and the organization is solid.	2 / 3
	Total	10 / 12 Passed

Description

67%

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 and occupies a distinct niche, but it omits an explicit 'Use when...' trigger clause and natural trigger-term coverage, relying on the separate activation block for triggers. Adding explicit trigger guidance would lift completeness and trigger_term_quality.

Suggestions

Append an explicit 'Use when the user asks to set up, install, enable, or initialize the commitments tracking system' clause to the description so the 'when' is stated, not implied.

Surface 1-2 natural trigger phrases (e.g. 'set up commitments', 'install commitments tracking') directly in the description text rather than only in activation.keywords, to improve trigger-term quality.

Keep the exclusion-marker sentence but consider trimming it slightly; the activation logic it describes already lives in the frontmatter, so the description can stay focused on what/when.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Creates workspace structure, schema docs, and installs triage and digest missions' — matching the multiple-specific-actions anchor; not a 2 because it enumerates several distinct actions rather than naming only a domain.	3 / 3
Completeness	Clearly states what the skill does, but the 'when' is only implied via 'one-time setup' and the exclusion-marker note rather than an explicit 'Use when...' clause; the judging guideline caps completeness at 2 when explicit trigger guidance is missing, so it is not a 3.	2 / 3
Trigger Term Quality	Contains domain-relevant terms like 'commitments tracking system' and 'setup' that a user might say, but the description itself lacks the explicit 'Use when...' trigger phrasing and common variations (those live in the separate activation.keywords block, not the description field); not a 3 because natural trigger coverage is only partial.	2 / 3
Distinctiveness Conflict Risk	Targets a clearly specific niche — 'commitments tracking system' one-time setup — and the exclusion-marker logic makes it unlikely to fire for unrelated skills; not a 2 because the niche is genuinely distinct rather than merely 'somewhat specific'.	3 / 3
	Total	10 / 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-setup/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.