CtrlK
BlogDocsLog inGet started
Tessl Logo

project-shepherd

Creates and manages project artifacts including project charters, Gantt-style timelines, RACI matrices, risk registers, and stakeholder communication plans. Tracks milestones, deadlines, resource allocation, and budget variance across cross-functional teams. Generates status reports, facilitates change control, and produces lessons-learned documentation. Use when a user needs to plan a new project, build a project plan or roadmap, track milestone progress, write a status update, conduct a risk assessment, allocate resources across teams, coordinate cross-functional delivery, or align stakeholders on scope, timeline, or budget changes.

93

Quality

92%

Does it follow best practices?

Impact

Pending

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Quality

Discovery

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

This is an excellent skill description that thoroughly covers the project management domain with specific, concrete actions and artifacts. It includes a comprehensive 'Use when...' clause with multiple natural trigger scenarios. The description uses proper third-person voice throughout and balances detail with clarity, making it highly effective for skill selection among a large pool of available skills.

DimensionReasoningScore

Specificity

Lists multiple specific concrete actions: creates project charters, Gantt-style timelines, RACI matrices, risk registers, stakeholder communication plans, tracks milestones/deadlines/resource allocation/budget variance, generates status reports, facilitates change control, and produces lessons-learned documentation.

3 / 3

Completeness

Clearly answers both 'what' (creates charters, timelines, RACI matrices, risk registers, etc.) and 'when' with an explicit 'Use when...' clause listing eight distinct trigger scenarios including planning projects, tracking milestones, writing status updates, and conducting risk assessments.

3 / 3

Trigger Term Quality

Excellent coverage of natural terms users would say: 'project plan', 'roadmap', 'milestone', 'status update', 'risk assessment', 'resource allocation', 'Gantt', 'RACI', 'stakeholder', 'budget', 'timeline', 'scope'. These are all terms a user would naturally use when requesting project management help.

3 / 3

Distinctiveness Conflict Risk

Occupies a clear niche in project management with highly specific artifacts (RACI matrices, Gantt timelines, risk registers, project charters) that are unlikely to overlap with other skills. The domain-specific terminology creates strong differentiation.

3 / 3

Total

12

/

12

Passed

Implementation

85%

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

This is a strong skill that provides highly actionable, well-structured project management guidance. The workflow is clearly sequenced with appropriate gates (intake validation, change control approval before updates), and the templates give Claude concrete output formats. Minor verbosity in the introductory section and some template placeholders that could be trimmed, but overall the content is well-calibrated for its complexity.

DimensionReasoningScore

Conciseness

The skill is reasonably well-structured but includes some content that could be tightened. The templates, while useful, are somewhat verbose with placeholder patterns that Claude could infer. The 'What This Skill Does' section is unnecessary preamble. However, most content earns its place as project management requires specific structural guidance.

2 / 3

Actionability

Highly actionable — provides complete, filled-in template skeletons with specific fields, concrete formatting (health indicators, variance notation like '+5 days vs. baseline'), and explicit rules for handling unknowns ([TBD — owner: <role>]). The change control process includes specific options and decision tracking. Every section tells Claude exactly what to produce.

3 / 3

Workflow Clarity

The 4-step workflow (Intake → Produce → Surface Decisions → Iterate) is clearly sequenced with explicit validation: Step 1 requires minimum inputs before proceeding, Step 2 mandates no generic placeholders, Step 3 forces surfacing blockers after every artifact, and the change control section explicitly gates updates behind approval ('Do not update milestones... until the change request is recorded as approved').

3 / 3

Progressive Disclosure

Well-organized with a clear overview table mapping requests to outputs, compact template skeletons inline, and a reference to TEMPLATES.md for full filled-in examples. The structure uses headers, tables, and collapsible detail levels effectively. Navigation is straightforward with one-level-deep references.

3 / 3

Total

11

/

12

Passed

Validation

90%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation10 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

10

/

11

Passed

Repository
OpenRoster-ai/awesome-agents
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.