CtrlK
BlogDocsLog inGet started
Tessl Logo

personwise/personwise-sop-process-training

SOPs get skimmed once and forgotten — until someone skips a step. Turn your SOP and policy documents into an interactive digital-human process training course that teaches the procedure exactly as written and answers questions against the source. The course always names the SOP version it teaches and never replaces supervision, licenses, or sign-off.

64

Quality

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Overview
Quality
Evals
Security
Files

Quality

Content

70%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 highly actionable, well-sequenced workflow with strong validation and error-recovery feedback loops, anchored by copy-paste-ready CLI commands. Its weaknesses are repetition that hurts conciseness and a monolithic inlined structure that limits progressive disclosure.

Suggestions

Deduplicate repeated rules (e.g. the awaiting_sources no-op behavior and "never create a replacement run") so each appears once and is cross-referenced, trimming token cost.

Provide one complete blueprint.json example block in addition to the field list to close the actionability gap.

Move the detailed CLI state-machine and conflict-recovery reference into a separate REFERENCES.md, leaving SKILL.md as a concise overview that links one level deep.

DimensionReasoningScore

Conciseness

Mostly efficient operational detail that Claude could not infer, but several rules are repeated verbatim ("never create a replacement run", "running and waiting are not failures", the awaiting_sources no-op behavior each stated twice) and could be tightened; not a 4 due to this noticeable repetition.

3 / 5

Actionability

Provides many copy-paste-ready `personwise ... --json` commands covering the common path, with a minor gap: the blueprint is described as a field list rather than shown as a complete JSON example.

4 / 5

Workflow Clarity

A clearly sequenced multi-step workflow with explicit validation checkpoints (readiness, source status, run wait at paused) and feedback loops for error recovery (retry_source, detach, read_current_state on CONFLICT, poll-after retry), matching the top anchor.

5 / 5

Progressive Disclosure

Section headers and one-level references to real bundle files (assets/bootstrap.sh, assets/bootstrap.ps1) are clear, but roughly 300 lines of CLI state-machine and error-handling detail are inlined in SKILL.md rather than split into separate reference files.

3 / 5

Total

15

/

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, explicit description that pairs a clear capability statement with concrete trigger language and good synonym coverage. It is mostly distinct, with only minor broadening at the end that raises slight conflict risk.

DimensionReasoningScore

Specificity

Lists several concrete actions ("Produce a grounded interactive digital-human course learners can interrupt with voice questions", "install or update the official PersonWise CLI and uses browser OAuth") with only minor coverage gaps; not a 5 because the core capability is bundled into a single course-creation action.

4 / 5

Completeness

Clearly answers both what ("Produce a grounded interactive digital-human course...") and when ("Use when the user asks for SOP and Process Training...") with concrete trigger phrases, matching the top anchor.

5 / 5

Trigger Term Quality

Explicit trigger language covers four natural synonyms ("SOP training; process training; procedure training; policy training") a user would say; a few natural variations (e.g. "standard operating procedure", "work instruction") are absent, so not a 5.

4 / 5

Distinctiveness Conflict Risk

A clear niche (SOP/process training via PersonWise CLI) with distinct triggers, but the closing "Other course-creation requests are handled only when the user explicitly asks for them with this Skill" creates minor overlap risk with general course-creation skills.

4 / 5

Total

17

/

20

Passed

Validation

93%

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

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

Total

15

/

16

Passed

Reviewed

Table of Contents

DiscoveryImplementationValidation