CtrlK
BlogDocsLog inGet started
Tessl Logo

pantheon-ai/retrospect-domain

Extract domain insights, patterns, and learnings from captured sessions for long-term knowledge retention.

63

Quality

79%

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Advisory

Suggest reviewing before use

Overview
Quality
Evals
Security
Files

Quality

Content

65%

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

A well-structured, mostly actionable body with a concrete script call and report template. It loses points for repeated "project-configurable" notes, implicit validation checkpoints, and a referenced file that is absent from the bundle.

Suggestions

State the "project-configurable" path convention once near the top and remove the repeated Notes in steps 1, 2, and 6.

Add an inline validation checkpoint after loading sessions (e.g. "If no sessions returned, stop and tell the user") so the zero-session guard is part of the workflow, not a separate section.

Either create references/reference.md and scripts/retrospect-load-sessions.sh in the bundle or drop the References link to avoid a dangling, unresolvable reference.

DimensionReasoningScore

Conciseness

The body is largely lean and well-sectioned, but the "project-configurable" note repeats across steps 1, 2, and 6 and the Gotchas section rehashes the PERIOD-header parsing point already made in step 2, so it could be tightened.

2 / 3

Actionability

It gives an executable script invocation (bash ${CLAUDE_PLUGIN_ROOT}/scripts/retrospect-load-sessions.sh $@), a concrete output path, a full report-format template, and copy-paste usage examples.

3 / 3

Workflow Clarity

The seven steps form a clear sequence with a step-1 fallback, but validation checkpoints are implicit: the zero-session guard lives in "When Not to Use" and PERIOD parsing is a gotcha rather than an inline checkpoint, so checkpoints are missing or implicit.

2 / 3

Progressive Disclosure

Sections are well-organized and the References link is one-level-deep and clearly signaled, but the referenced references/reference.md and the scripts/retrospect-load-sessions.sh do not exist in the bundle, so navigation does not resolve.

2 / 3

Total

9

/

12

Passed

Description

90%

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 voice, explicit what-and-when, and natural trigger terms. The only weakness is that the capability verbs are somewhat abstract rather than naming concrete operations.

Suggestions

Swap one abstract verb for a concrete operation to lift specificity, e.g. "extract WHAT/WHY learnings from session files and synthesize cross-session patterns into a Start/Stop/Continue report."

DimensionReasoningScore

Specificity

"Analyze domain insights (WHAT/WHY learned) from captured sessions" and "reviewing learnings, extracting patterns, analyzing decisions" name the domain and several actions, but the verbs operate on abstract nouns rather than concrete operations, matching the anchor that names domain and some actions without being comprehensive.

2 / 3

Completeness

It explicitly answers both what ("Analyze domain insights... from captured sessions") and when ("Use when reviewing learnings... Triggers include..."), with explicit trigger guidance.

3 / 3

Trigger Term Quality

"what did I learn", "session insights", "domain analysis", and "retrospect domain" are natural phrases a user would actually say, giving good coverage of trigger terms.

3 / 3

Distinctiveness Conflict Risk

The WHAT/WHY domain-insights framing carves a clear niche distinct from a collaboration-focused sibling, and the triggers ("domain analysis", "what did I learn") are unlikely to fire for the wrong skill.

3 / 3

Total

11

/

12

Passed

Validation

75%

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

Validation12 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

frontmatter_unknown_keys

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

Warning

relative_links

Relative link issues: 1 missing

Warning

referenced_paths_exist

Referenced path issues: 1 missing

Warning

Total

12

/

16

Passed

Reviewed

Table of Contents