CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

qcon-sf-2026-skill-issue

Summarize or answer questions about Baruch Sadogursky's QCon San Francisco 2026 workshop Skill Issue: How to Write Skills That Actually Work, including its Brickbox examples, rehearsal results, and lessons about agent skills.

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

Fix and improve this skill with Tessl

tessl review fix ./_skills/qcon-sf-2026-skill-issue/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

85%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, lean knowledge-brief skill with a clear two-step gating workflow and explicit exit conditions. The fact base is specific and non-redundant; the only minor gaps are a couple of sentences that could be tightened and slightly abstract phrasing in the answering guidance.

DimensionReasoningScore

Conciseness

The body is dense with workshop-specific facts Claude cannot know (rehearsal timings, scorecard results, hook behavior) and avoids explaining general concepts, but a few sentences could be trimmed (e.g. "Dollar costs require prices or billing records"), matching the efficient-with-minor-trims anchor.

4 / 5

Actionability

For an instruction-only Q&A skill the guidance is concrete: "Keep workshop plans and recorded rehearsal results distinct", "Use a linked source if asked for details beyond this brief", and explicit exit conditions, backed by a detailed fact base; only "Answer at the depth the question calls for" is somewhat vague, so it falls just short of fully executable guidance.

4 / 5

Workflow Clarity

A simple single-task skill with explicitly ordered steps ("Process steps in order. Do not skip ahead") and a built-in checkpoint and exit in Step 1 ("If they mean another delivery, finish here"), plus a clear finish condition; per the simple-skill note this earns the top score, and no destructive or batch operations apply.

5 / 5

Progressive Disclosure

The body is under 50 lines with well-organized sections (steps, talk brief subsections, sources) and no need for external reference files; the only links are clearly signaled one-level-deep source URLs, which per the simple-skill note merits the top score.

5 / 5

Total

18

/

20

Passed

Description

65%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 highly distinctive, well-targeted description for a single-event knowledge skill, with good natural trigger terms. Its main weakness is the absence of an explicit 'Use when...' clause and its reliance on only two generic action verbs.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user asks about the Skill Issue workshop, Baruch Sadogursky's QCon SF talk, or its Brickbox examples."

Replace the generic "Summarize or answer questions about" with more concrete capabilities, e.g. "Explains the Brickbox double-charge case, the description-vs-instructions lesson, routing timings, and eval scorecard results from the workshop."

DimensionReasoningScore

Specificity

The description names a precise domain ("Baruch Sadogursky's QCon San Francisco 2026 workshop Skill Issue") but only lists two generic actions ("Summarize or answer questions about"), matching the anchor for domain plus 1-2 concrete actions without comprehensive coverage.

3 / 5

Completeness

The 'what' is clear (summarize/answer questions about this specific workshop), but there is no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines; the 'when' is only weakly implied by naming the workshop.

3 / 5

Trigger Term Quality

Strong natural keywords a user would actually say ("Baruch Sadogursky", "QCon San Francisco 2026", "Skill Issue", "Brickbox", "agent skills"), but a few natural variations like "the workshop" or "the talk" are missing, fitting the good-but-not-comprehensive anchor.

4 / 5

Distinctiveness Conflict Risk

The description targets a single named workshop, presenter, and date, giving it a clear niche with distinct triggers and minimal risk of firing for unrelated skills, matching the top anchor.

5 / 5

Total

15

/

20

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

jbaruch/shownotes

Path

_skills/qcon-sf-2026-skill-issue/SKILL.md

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.