project-graveyard

Scans the developer's machine for dead side projects, autopsies each one from its git history (died at the payments wall, killed by a newer project, finished but never shipped), surfaces their personal death patterns, and picks the corpse most worth resurrecting — then helps ship it. Use when the user mentions abandoned, unfinished, or old side projects, asks "what should I finish", wants to revive or resurrect a project, says "run the graveyard", wonders why they never finish anything, or is about to start a new project that sounds like one they already built. Runs entirely locally.

Quality

90%

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

Quality

Content

81%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.

A well-structured, opinionated skill body with concrete commands, a clearly sequenced workflow including validation checkpoints, and proper one-level-deep reference file usage. The main weakness is mild verbosity in the formatting/epitaph-spec sections.

Suggestions

Tighten the tombstone card and epitaph-rules sections — the ASCII card column-width spec and four epitaph rules could be compressed without losing the intent.

Make the world-check step more concrete with an explicit search-and-cite loop (e.g. 'search the API/SDK named in the evidence; record found vs. not-found') rather than prose guidance.

Add an explicit verify-and-retry checkpoint around the resurrection plan's Step 0 ('confirm it still runs') so failure produces a defined next action rather than just a stated requirement.

Dimension	Reasoning	Score
Conciseness	Mostly lean and assumes Claude's competence (e.g. 'two questions is a conversation; five is a deposition'), with some sections that could be trimmed — the epitaph rules and tombstone card spec are wordy relative to the core workflow.	4 / 5
Actionability	Executable commands throughout (the run invocation, --days/--json/--me/--include-foreign/--state flags, the --mark-resurrected recording step) with concrete examples; the ASCII card is a precise spec, though the world-check step relies on search rather than a runnable command.	4 / 5
Workflow Clarity	Clear multi-step sequence (scan -> read report -> interview -> tombstone report -> world-check -> resurrection plan -> record state) with explicit validation checkpoints (Step 0 'confirm it still runs', 'ask before touching the repo', evidence-before-repeating-a-cause); capped below 5 because some checkpoints are prose rather than a verify-and-retry loop.	4 / 5
Progressive Disclosure	Well-organized overview in SKILL.md with one-level-deep, clearly signaled references to scripts/graveyard.py and references/causes-of-death.md, both of which exist as real bundle files; the taxonomy is correctly offloaded to the reference rather than inlined.	5 / 5
	Total	17 / 20 Passed

Description

100%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.

A high-quality description that concretely states multiple capabilities, supplies explicit and natural 'Use when' trigger phrases, and stakes out a clearly distinct niche. It is detailed without padding and answers both what and when.

Dimension	Reasoning	Score
Specificity	Multiple concrete actions named (scans machine, autopsies each from git history, surfaces death patterns, picks a corpse to resurrect, helps ship it) with comprehensive coverage rather than generic phrasing.	5 / 5
Completeness	Explicitly answers what ('Scans the developer's machine for dead side projects, autopsies each... picks the corpse most worth resurrecting — then helps ship it') and when ('Use when the user mentions abandoned...') with concrete trigger phrases, plus a locality constraint.	5 / 5
Trigger Term Quality	Comprehensive natural trigger phrases users would actually say ('abandoned, unfinished, or old side projects', 'what should I finish', 'revive or resurrect', 'run the graveyard', 'why they never finish anything'), plus the prior-project-overlap case.	5 / 5
Distinctiveness Conflict Risk	Clear niche (dead local side projects + git autopsy + resurrection) with highly distinct triggers unlikely to fire for the wrong skill; runs entirely locally distinguishes it further.	5 / 5
	Total	20 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: Shubhamsaboo/awesome-llm-apps
Path: agent_skills/project-graveyard/SKILL.md
Commit: 813a55e

Reviewed: 1 day 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.