project-planner
Detects stale project plans and suggests session commands. Triggers on: sync plan, update plan, check status, plan is stale, track progress, project planning.
77
66%
Does it follow best practices?
Impact
94%
1.54xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./data/skills-md/0xdarkmatter/claude-mods/project-planner/SKILL.mdQuality
Discovery
82%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 functional with a clear 'Triggers on' clause that provides explicit trigger terms, which is a strength. However, the 'what' portion is somewhat vague — 'suggests session commands' is unclear without more context about what those commands are or what the skill actually does in practice. The trigger terms are well-chosen but a couple are generic enough to risk overlap with other planning-related skills.
Suggestions
Clarify what 'suggests session commands' means concretely — e.g., 'suggests TODO updates, milestone completions, or plan revision commands'
Add more specificity to the capability description, such as what 'stale' means (e.g., outdated milestones, missed deadlines) and what outputs the skill produces
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (project plans) and two actions (detects stale plans, suggests session commands), but lacks detail on what 'suggests session commands' means concretely or what specific operations are performed. | 2 / 3 |
Completeness | Clearly answers both 'what' (detects stale project plans and suggests session commands) and 'when' (explicit 'Triggers on:' clause with specific trigger phrases), satisfying the requirement for explicit trigger guidance. | 3 / 3 |
Trigger Term Quality | Includes a good set of natural trigger terms users would say: 'sync plan', 'update plan', 'check status', 'plan is stale', 'track progress', 'project planning' — these cover common variations well. | 3 / 3 |
Distinctiveness Conflict Risk | The terms 'project planning' and 'track progress' are somewhat generic and could overlap with general project management or task tracking skills. However, the specific focus on 'stale plans' and 'session commands' provides some distinctiveness. | 2 / 3 |
Total | 10 / 12 Passed |
Implementation
50%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides a clear conceptual framework for detecting stale project plans and suggesting commands, with a useful quick reference table. However, it lacks executable implementation code for the detection logic and has some redundancy between the detection examples and staleness heuristics sections. The skill reads more like a design document than actionable instructions Claude can follow.
Suggestions
Add executable code (bash/Python) for the core detection logic, e.g., comparing `stat -c %Y docs/PLAN.md` against `git log --since` to determine staleness.
Consolidate the 'Detection Logic' examples and 'Staleness Heuristics' sections to eliminate redundancy — the heuristics should be embedded in the detection logic rather than restated separately.
Add a clear sequential workflow: 1) Check if PLAN.md exists, 2) If yes, check staleness, 3) Check git status, 4) Output appropriate suggestion — with explicit decision points.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably concise but includes some unnecessary framing (e.g., 'This skill does NOT manage plans directly' and the Purpose section explaining what it doesn't do). The 'Staleness Heuristics' section partially duplicates the detection logic examples above it. | 2 / 3 |
Actionability | The skill provides concrete command suggestions and a useful quick reference table, but lacks executable code for the detection logic itself. The detection examples are pseudocode-like descriptions rather than actual implementation, and there's no concrete code showing how to check staleness (e.g., comparing git log dates to file modification times). | 2 / 3 |
Workflow Clarity | The detection scenarios are clearly enumerated with trigger conditions and suggested actions, but there's no sequenced workflow for how Claude should actually perform detection. It's more of a lookup table than a process flow, and there are no validation or feedback steps for verifying whether suggestions were appropriate. | 2 / 3 |
Progressive Disclosure | The content is well-organized with clear sections and a reference table, but with no bundle files, there are no references to deeper documentation. The staleness heuristics section could be separated or the detection logic and heuristics could be better consolidated to avoid partial duplication. | 2 / 3 |
Total | 8 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- NeverSight/skills_feed
- Commit
2d09b29
- Reviewed
Table of Contents
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.