implement-posix-command

Implement a new POSIX command as a builtin in the safe shell interpreter

Quality

65%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/implement-posix-command/SKILL.md

Quality

Content

77%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 skill body is exceptionally actionable and its 10-step gated workflow with validation checkpoints is a model of clarity. Its weaknesses are conciseness (repeated boilerplate and inlined reference material) and progressive disclosure (a 610-line monolith with no external reference files).

Suggestions

Extract the GNU reference-output capture guide (Step 4) and the fuzz seed-corpus sourcing detail (Step 9) into separate reference files and link to them one level deep to improve progressive disclosure.

De-duplicate the repeated GATE CHECK / parallel-step boilerplate into a single shared 'Execution protocol' reference at the top rather than restating it before every step.

Tighten the security preamble and context sections to assume Claude's competence, keeping only the untrusted-data handling rules that are non-obvious.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and concrete, but at ~610 lines it repeats gate-check language across steps and inlines verbose reference material (GNU-compat capture instructions, fuzz-corpus sourcing) that could be tightened or externalized.	3 / 5
Actionability	It provides fully executable, copy-paste-ready Go test helpers, YAML scenario templates, shell commands, and concrete flag/edge-case tables covering the common and tricky cases.	5 / 5
Workflow Clarity	The 10-step process is explicitly sequenced with parallel/sequential gating, TaskList gate checks before every step, validation checkpoints ('go test', 'Validate immediately'), and fix-retry feedback loops for destructive operations.	5 / 5
Progressive Disclosure	Content is organized into clear sections but is monolithic: no bundle/reference files exist, and substantial material (GNU equivalence capture, fuzz seed-corpus sourcing) that belongs in one-level-deep reference files is inlined in SKILL.md.	3 / 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 is a clear, third-person statement of what the skill does but stops at a single generic action and omits any 'Use when' trigger guidance. It is distinct enough to avoid most conflicts but would benefit from listing concrete actions and explicit trigger terms.

Suggestions

Add a 'Use when...' clause naming concrete trigger phrases (e.g. 'Use when adding a new POSIX utility to the safe shell, or when the user asks to implement a coreutils-style command as a builtin').

Expand the single action into several specific ones (e.g. research POSIX behavior, generate gated test suites, register the builtin, harden against DoS) to raise specificity.

Include natural synonyms and file extensions users would say (e.g. 'coreutils command', 'shell builtin', '.go implementation') to improve trigger-term quality.

Dimension	Reasoning	Score
Specificity	It names the domain ('POSIX command', 'builtin', 'safe shell interpreter') and one concrete action ('Implement') in third-person voice, but offers only a single generic action rather than a list of specific concrete capabilities.	3 / 5
Completeness	It has a clear 'what' (implement a POSIX command as a builtin) but no 'when'/Use-when guidance; per the judging guidelines, a missing explicit trigger clause caps completeness at 3.	3 / 5
Trigger Term Quality	Relevant terms like 'POSIX command', 'builtin', and 'safe shell interpreter' are present, but it lacks the natural trigger phrases a user would actually say and offers no synonyms or file extensions.	3 / 5
Distinctiveness Conflict Risk	The niche is fairly specific — implementing POSIX commands as builtins in the safe shell interpreter — and unlikely to be confused with unrelated skills, with only minor overlap risk against other interpreter-related skills.	4 / 5
	Total	13 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (611 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: DataDog/rshell
Path: .claude/skills/implement-posix-command/SKILL.md
Commit: 30a7e9e

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.