new-project

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

Quality

64%

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

75%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 body delivers a clear, actionable, well-structured setup workflow with concrete tool-call templates and explicit sequencing rules. Its main gaps are placeholder-style examples and only lightweight validation rather than full error-recovery feedback loops.

Suggestions

Add an explicit validation/checkpoint after the writes (e.g., verify each memory_write succeeded before proceeding and confirm missions were created with the correct project_id) to support a feedback loop.

Provide at least one fully filled-in worked example (a concrete slug, AGENTS.md content, and mission_create call) to make the templates copy-paste ready.

Tighten a few explanatory sentences (e.g., the AGENTS.md note and Rules) to push conciseness toward fully lean.

Dimension	Reasoning	Score
Conciseness	The body is lean and task-focused with minimal padding; brief notes like "This file is loaded into the system prompt…" earn their place, though a few sentences could still be trimmed, fitting level 4 rather than the fully lean level 5.	4 / 5
Actionability	Concrete memory_write and mission_create templates with real target paths and parameter guidance are provided; they use fill-in placeholders rather than literal copy-paste code, leaving minor gaps versus level 5.	4 / 5
Workflow Clarity	Four steps are explicitly sequenced with a one-call-at-a-time rule and a final 'summarize what was created' verification; validation is present but lightweight with no error-recovery feedback loop, so level 4 fits better than 5.	4 / 5
Progressive Disclosure	Content is well-organized into clear sections (procedure, structure convention, rules) and is self-contained with no bundle files; at ~70 lines it slightly exceeds the simple-skill threshold, so it lands at 4 rather than 5.	4 / 5
	Total	16 / 20 Passed

Description

53%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 clearly states the skill's purpose and exposes a distinct slash-command trigger, but it omits explicit scenario-based "when to use" guidance and natural synonyms, which limit completeness and trigger-term quality.

Suggestions

Add an explicit 'Use when…' clause naming concrete scenarios (e.g., 'Use when the user wants to set up or organize work into a recurring autonomous project workspace').

Broaden trigger coverage with synonyms like 'set up project', 'organize into a project', and 'autonomous workspace'.

Optionally enumerate one or two more concrete actions (e.g., 'write project context, goals, and recurring missions') to raise specificity.

Dimension	Reasoning	Score
Specificity	"Create and structure a new autonomous project" names the domain plus two concrete actions (create, structure), matching the level-3 anchor; it does not list several specific actions needed for level 4.	3 / 5
Completeness	The "what" is clear (create and structure a project), but there is no explicit "Use when…" scenario clause; the slash command only weakly implies the trigger, so completeness is capped at 3 per the guideline.	3 / 5
Trigger Term Quality	Includes the natural phrase "new project" and the "/new-project" slash command, but lacks common synonyms (e.g. "set up", "workspace", "organize") that would warrant level 4.	3 / 5
Distinctiveness Conflict Risk	"Autonomous project" workspace framing plus a distinct "/new-project" command carve a clear niche with only minor overlap risk against generic project skills.	4 / 5
	Total	13 / 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: nearai/ironclaw
Path: skills/new-project/SKILL.md
Commit: 2831516

Reviewed: 8 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.