cognitive-walkthrough-beads
Skill19 starsChanged 6 days agoMITView on GitHub
Run a cognitive walkthrough and create Beads issues from the findings. Converts walkthrough breakdowns (Q1-Q4 failures) into trackable Beads tasks with priorities and dependencies.
- Installs packages
In this repository67 other files it gives its agents.
- accessibility-precheckSkill
- cognitive-friction-detectorSkill
- cognitive-walkthrough-beadsSkill
- cognitive-walkthroughSkill
- conceptual-model-beadsSkill
- conceptual-modelSkill
- consistency-audit-beadsSkill
- consistency-auditSkill
- error-and-time-metrics-analyzerSkill
- failure-path-audit-beadsSkill
- failure-path-auditSkill
- field-study-plannerSkill
- heuristic-eval-beadsSkill
- heuristic-evalSkill
- high-fidelity-prototype-plannerSkill
- information-architecture-beadsSkill
- information-architectureSkill
- interaction-type-selectorSkill
- journey-map-beadsSkill
- journey-mapSkill
- low-fidelity-prototype-plannerSkill
- mental-model-checkerSkill
- persona-synthesizerSkill
- prototype-hci-pack-beadsSkill
- prototype-hci-packSkill
- representative-task-writerSkill
- satisfaction-questionnaire-writerSkill
- state-model-beadsSkill
- state-modelSkill
- task-analysis-writerSkill
- usability-test-plannerSkill
- vocabulary-audit-beadsSkill
- vocabulary-auditSkill
- wireframe-criticSkill
- accessibility-precheckSkill
- cognitive-friction-detectorSkill
- cognitive-walkthroughSkill
- conceptual-model-beadsSkill
- conceptual-modelSkill
- consistency-audit-beadsSkill
- consistency-auditSkill
- error-and-time-metrics-analyzerSkill
- failure-path-audit-beadsSkill
- failure-path-auditSkill
- field-study-plannerSkill
- heuristic-eval-beadsSkill
- heuristic-evalSkill
- high-fidelity-prototype-plannerSkill
- information-architecture-beadsSkill
- information-architectureSkill
- interaction-type-selectorSkill
- journey-map-beadsSkill
- journey-mapSkill
- low-fidelity-prototype-plannerSkill
- mental-model-checkerSkill
- persona-synthesizerSkill
- prototype-hci-pack-beadsSkill
- prototype-hci-packSkill
- representative-task-writerSkill
- satisfaction-questionnaire-writerSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
12 rules. About 0 are common, 7 are distinctive, and 5 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈7
Distinctive · estimate
This author's own choices. Worth a look.
5
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 8
Run a Cognitive Walkthrough on the current prototype, then create Beads issues from the findings so they become trackable tasks.
- Distinctive: line 16
Run a cognitive walkthrough for this task or flow:
- Distinctive: line 20
Use ultrathink. Act like a plausible first-time user with only the cues available in the interface.
- Very specific: line 23
Write docs/hci/cognitive-walkthrough.md unless the user asked for another path.
- Distinctive: line 24
Create the directory if it does not exist.
- Distinctive: line 30
After acting, will the feedback make sense?
- Very specific: line 70
Check if the bd CLI is available:
- Very specific: line 76
If
bdis not found: Stop here. Output the Cognitive Walkthrough only, and append: - Distinctive: line 93
Check if the repo is already initialized:
- Very specific: line 99
If that fails (no .beads/ directory, not initialized):
- Very specific: line 105
Use --stealth so Beads metadata is not committed to the main repo.
- Distinctive: line 109
Create one parent issue to group all findings from this walkthrough:
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Run a Cognitive Walkthrough on the current prototype, then create Beads issues from the findings so they become trackable tasks.
This is an add-on to cognitive-walkthrough. Run the full walkthrough first, produce the complete artifact, then pipe findings into Beads.
Phase 1: Run the Cognitive Walkthrough
Run a cognitive walkthrough for this task or flow:
$ARGUMENTS
Use ultrathink. Act like a plausible first-time user with only the cues available in the interface. Use the actual prototype and codebase context.
Output
Write docs/hci/cognitive-walkthrough.md unless the user asked for another path.
Create the directory if it does not exist.
Required questions at every step
- Will the user form the right goal here?
- Will the user notice the correct action?
- Will the user understand that the action leads toward the goal?
- After acting, will the feedback make sense?
Required format
For each step include:
- step number
- user goal
- visible cues
- likely action
- walkthrough answers for Q1 to Q4
- breakdowns / confusion risks
- recommendation
Extra checks
Also flag:
- hidden prerequisites
- unclear affordances
- weak or missing feedback
- misleading labels
- dead ends
- unclear recovery path
Synthesis
End with:
- steps most likely to fail
- reasons first-time users may hesitate
- design changes most likely to improve task completion
Deliverable style
- Clear headings
- Markdown tables
- Mermaid diagrams where useful
- Direct language
- No filler
Phase 2: Beads Integration
Step 1 -- Detect Beads
Check if the bd CLI is available:
command -v bdIf bd is not found: Stop here. Output the Cognitive Walkthrough only, and append:
## Beads Integration: Skipped
`bd` CLI not found. To install Beads and create trackable issues from this review:
pip install beads-cli
# or see https://github.com/steveyegge/beads
Then re-run: /cognitive-walkthrough-beadsIf bd is found: Continue to Step 2.
Step 2 -- Initialize Beads (if needed)
Check if the repo is already initialized:
bd ready --jsonIf that fails (no .beads/ directory, not initialized):
bd init --stealthUse --stealth so Beads metadata is not committed to the main repo.
Step 3 -- Create parent issue
Create one parent issue to group all findings from this walkthrough:
bd create "Cognitive Walkthrough: <branch> — <scope>" -p 1 --jsonCapture the parent issue ID from the JSON output. Store scope and summary:
bd update <parent-id> --description "<1-2 sentence scope summary>" --acceptance "<quality bar from the review>" --notes "Review date: <today>. Scope: <arguments>."Step 4 -- Create child issues per finding
For each walkthrough breakdown (Q1-Q4 failures):
MAJOR findings -- always create:
Steps where users cannot form goal or notice action (Q1/Q2 failures):
bd create "[MAJOR] <finding-title>" -p 0 --jsonMINOR findings -- create only if the user passed --include-minor. Otherwise skip and note them in the output.
Weak feedback or unclear interpretation (Q3/Q4 issues):
bd create "[MINOR] <finding-title>" -p 2 --jsonFor each created issue, update with structured fields (do NOT use bd edit):
bd update <child-id> --description "<what/why + evidence>" --notes "<location and context>" --acceptance "<fix recommendation or verification>"Then link child to parent:
bd dep add <child-id> <parent-id>Step 5 -- Show next actions
bd ready --jsonOutput
Return a combined report with two sections:
Section A: Cognitive Walkthrough
- Per-step walkthrough (goal, cues, action, Q1-Q4 answers, breakdowns, recommendations)
- Extra checks (hidden prerequisites, unclear affordances, weak feedback, dead ends)
- Synthesis (steps most likely to fail, first-time user hesitation points, design changes)
Section B: Beads Integration Summary
- Status: initialized | already-initialized | skipped (with reason)
- Parent bead:
<id>--<title> - Created beads: table of Bead ID | Severity | Finding Title | Priority
- Skipped findings: list with reasons (e.g., "MINOR, --include-minor not set")
- Next actions: output of
bd ready --json
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

