new-project

Create and structure a new autonomous project — "/new-project <what project does>"

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/new-project/SKILL.md

Quality

Content

87%

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

The body is concise, actionable, and well-structured with concrete tool calls, but the multi-step workflow lacks any verification checkpoints that would push it to fully robust.

Suggestions

Add a final verification step such as confirming the project files exist and that missions were created under the intended project_id rather than Default.

Note an error-recovery path for when project_id fails to resolve or a memory_write target already exists.

Consider a short checklist recap after setup to make the workflow's completion state explicit.

Dimension	Reasoning	Score
Conciseness	The body is lean — tool-call blocks and a tight structure convention with no padding about concepts Claude already knows — so it matches the level-3 'lean and efficient' anchor rather than the level-2 'could be tightened' anchor.	3 / 3
Actionability	It provides concrete, parameterized `memory_write` and `mission_create` calls that are effectively copy-paste ready, matching the level-3 executable-code anchor rather than the pseudocode level-2 anchor.	3 / 3
Workflow Clarity	Steps are explicitly numbered and sequenced with reinforcing rules, but there are no validation or verification checkpoints (e.g., confirm files written, confirm project_id resolved), matching the level-2 'sequence present but checkpoints missing' anchor rather than the level-3 'explicit validation steps' anchor.	2 / 3
Progressive Disclosure	Content is well-organized into clearly signaled sections (step-by-step procedure, structure convention, rules) and is self-contained with no external references needed, matching the well-organized level-3 anchor for a compact skill.	3 / 3
	Total	11 / 12 Passed

Description

57%

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 clearly conveys a distinct niche and concrete invocation but is thin on action breadth and lacks an explicit situational "when" trigger, leaving it competent but not exemplary.

Suggestions

Expand the action list beyond 'Create and structure' to concrete capabilities (e.g., 'write AGENTS.md, context, and goals files; create recurring missions').

Add an explicit trigger clause such as 'Use when the user asks to create, set up, or organize a new project or autonomous workspace'.

Include natural trigger terms users would say ('new project', 'set up project', 'organize into a project') rather than only the slash-command form.

Dimension	Reasoning	Score
Specificity	Names two actions — "Create and structure" — but they are high-level and not a comprehensive list of concrete actions like the level-3 anchor, so it sits at level 2 rather than 3 and above the vague level-1 anchor.	2 / 3
Completeness	It states what ("Create and structure a new autonomous project") but gives only an invocation form, not an explicit "Use when..." situational clause; per guidelines a missing explicit when-clause caps completeness at 2.	2 / 3
Trigger Term Quality	The "/new-project <what project does>" invocation provides a concrete trigger but no natural-language keyword variations a user would actually say, matching level 2 (some relevant keywords, missing common variations) rather than the broad coverage of level 3.	2 / 3
Distinctiveness Conflict Risk	The narrow niche "new autonomous project" paired with the distinct "/new-project" slash-command trigger makes it unlikely to fire for the wrong skill, matching the level-3 clear-niche anchor.	3 / 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/new-project/SKILL.md
Commit: 800b781

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.