nasa-pm-lessons

Surface a matched excerpt from Jerry Madden's NASA project-management aphorisms (LLIS #1956) at the moment it fits: incident root-cause sections; ticket refinement; plan drafting; status updates; escalation calls. Loads only one category at a time — never the full list, never more than three aphorisms per response. DO NOT use this for regulatory, legal, or prize-dispute decisions; route those to Legal/Compliance/DPO. Triggers: 'root cause', 'refine this ticket', 'draft a plan', 'status update', 'should I escalate', 'stakeholder comms'.

Quality

77%

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/project-mgmt/nasa-pm-lessons/SKILL.md

Quality

Content

71%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 instruction-only skill: excellent progressive disclosure, clear scenario routing, and concrete citation guidance. The main costs are repetition of the same brevity/over-citing rule across five sections and a Verification section polluted with an out-of-place skill-auditor tool command.

Suggestions

Remove or relocate the `cargo run -p pantheon-skill-auditor` command and its B-grade note from the Verification section — it is authoring/tooling guidance, not skill-usage guidance, and is not executable in a conversation context.

Consolidate the over-citing warning: it currently appears in When Not to Use, Workflow, three Mindset bullets, two Anti-Patterns, and Troubleshooting. State the 1-3-aphorism limit once in the Workflow and keep one Anti-Pattern entry.

The Mindset and Troubleshooting sections largely restate each other (prefer zero citations over a forced fit) — merge them into a single short section to reclaim token budget.

Dimension	Reasoning	Score
Conciseness	The over-citing warning is repeated roughly six times across When Not to Use, Workflow, Mindset, Anti-Patterns, and Troubleshooting ("never more than three aphorisms", "brevity is the point", "treat over-citing as the gotcha"), and the Verification section embeds an irrelevant `cargo run -p pantheon-skill-auditor` audit command. Mostly efficient but clearly could be tightened — anchor 3, not 4.	3 / 5
Actionability	Concrete, executable guidance throughout: a scenario→file table, a numbered workflow with an exact citation format ("state the point in a line, attribute it to Madden/LLIS #1956"), a worked output example, and BAD/GOOD anti-pattern pairs. Held below 5 because the Verification section's cargo auditor command is not actionable mid-task and conflates tooling guidance with skill usage.	4 / 5
Workflow Clarity	The 4-step workflow (identify scenario → load the matching reference file → pick 1-3 fitting aphorisms → apply to the concrete case) is clearly sequenced, with a skip-if-no-fit recovery path in Troubleshooting and a confirmation checkpoint for regulated topics. Not 5: the Verification section mixes an external audit command with usage guidance, muddying the checkpoint.	4 / 5
Progressive Disclosure	The body is a lean overview that splits all aphorism content into six one-level-deep reference files, every referenced path exists in the bundle, and navigation is doubly signaled via the When to Use table and the References table. This matches the anchor-5 pattern of well-signaled one-level-deep references with easy navigation.	5 / 5
	Total	16 / 20 Passed

Description

83%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 strong description: third-person, concrete, with an explicit what, an explicit when including literal trigger phrases, and a clear do-not-use boundary. The only weaknesses are slightly thin synonym coverage in the triggers and a couple of broad trigger terms that could overlap with generic PM skills.

Dimension	Reasoning	Score
Specificity	"Surface a matched excerpt" plus "Loads only one category at a time — never the full list, never more than three aphorisms per response" names the domain and several concrete, specific behaviors. It falls short of anchor 5 because the categories of aphorisms available are not enumerated, but exceeds anchor 3's '1-2 concrete actions' bar.	4 / 5
Completeness	It explicitly answers both questions: what ("Surface a matched excerpt from Jerry Madden's NASA project-management aphorisms (LLIS #1956)") and when (scenario list — "incident root-cause sections; ticket refinement; plan drafting; status updates; escalation calls" — plus concrete trigger phrases). This matches the anchor-5 example pattern exactly.	5 / 5
Trigger Term Quality	Explicit triggers — 'root cause', 'refine this ticket', 'draft a plan', 'status update', 'should I escalate', 'stakeholder comms' — are natural phrases a user would actually say. Not anchor 5: common variations like 'postmortem', 'incident', 'retro', or 'standup' are absent.	4 / 5
Distinctiveness Conflict Risk	A clear niche (NASA PM aphorism citation) with an explicit "DO NOT use this for regulatory, legal, or prize-dispute decisions" boundary reduces mis-triggering. However, broad triggers like 'draft a plan' and 'status update' create minor overlap risk with generic PM/status skills, so it is not the anchor-5 'minimal conflict risk'.	4 / 5
	Total	17 / 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: pantheon-org/tekhne
Path: skills/project-mgmt/nasa-pm-lessons/SKILL.md
Commit: a1083f4

Reviewed: 3 hours 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.