Report a bug against an existing feature — creates a structured bugs.md record, generates fix tasks in tasks.md, and optionally imports from or creates GitHub issues. Use when fixing a bug, reporting a defect, importing a GitHub issue into the workflow, or triaging an error without running the full specification process.
From jm-adknpx claudepluginhub javimontano/jm-adk-alfaThis skill uses the workspace's default tool permissions.
agents/guardian.mdagents/lead.mdagents/specialist.mdagents/support.mdevals/evals.jsonknowledge/body-of-knowledge.mdknowledge/knowledge-graph.mdprompts/meta.mdprompts/primary.mdprompts/variations/deep.mdprompts/variations/quick.mdreferences/bugs-template.mdreferences/constitution-loading.mdreferences/model-recommendations.mdtemplates/output.docx.mdtemplates/output.htmlReport a bug against an existing feature, create a structured bugs.md record, and generate fix tasks in tasks.md. [EXPLICIT]
$ARGUMENTS
You MUST consider the user input before proceeding (if not empty). [EXPLICIT]
Load constitution per constitution-loading.md (soft mode — warn if missing, proceed without). [EXPLICIT]
The text after /iikit-bugfix is either a #number (GitHub issue) or a text bug description. [EXPLICIT]
Determine the input type: [EXPLICIT]
#number pattern (e.g., #42): GitHub inbound flow (Step 2a)/iikit-bugfix 'Login fails when email contains plus sign' or /iikit-bugfix #42If input contains BOTH #number and text, prioritize the #number and warn that text is ignored. [EXPLICIT]
gh issue view <number> --json title,body,labels if available, otherwise curl the GitHub API (GET /repos/{owner}/{repo}/issues/{number})title → bug descriptionbody → reproduction stepslabels → severity mapping: labels containing "critical" → critical, "high"/"priority" → high, "bug" → medium (default), otherwise → mediumRun feature listing: [EXPLICIT]
Unix/macOS/Linux:
bash .tessl/tiles/tessl-labs/intent-integrity-kit/skills/iikit-core/scripts/bash/bugfix-helpers.sh --list-features
Windows (PowerShell):
pwsh .tessl/tiles/tessl-labs/intent-integrity-kit/skills/iikit-core/scripts/powershell/bugfix-helpers.ps1 --list-features
Parse the JSON array. If empty: ERROR with "No features found. Run /iikit-01-specify first to create a feature." [EXPLICIT]
Present a numbered table of features: [EXPLICIT]
| # | Feature | Stage |
|---|---|---|
| 1 | 001-user-auth | implementing-50% |
| 2 | 002-api-gateway | specified |
Prompt user to select a feature by number. [EXPLICIT]
After selection, validate: [EXPLICIT]
Unix/macOS/Linux:
bash .tessl/tiles/tessl-labs/intent-integrity-kit/skills/iikit-core/scripts/bash/bugfix-helpers.sh --validate-feature "<feature_dir>"
Windows (PowerShell):
pwsh .tessl/tiles/tessl-labs/intent-integrity-kit/skills/iikit-core/scripts/powershell/bugfix-helpers.ps1 --validate-feature "<feature_dir>"
If invalid: ERROR with the message from the JSON response. [EXPLICIT]
For text input (2b):
For GitHub inbound (2a):
Unix/macOS/Linux:
bash .tessl/tiles/tessl-labs/intent-integrity-kit/skills/iikit-core/scripts/bash/bugfix-helpers.sh --next-bug-id "<feature_dir>"
Windows (PowerShell):
pwsh .tessl/tiles/tessl-labs/intent-integrity-kit/skills/iikit-core/scripts/powershell/bugfix-helpers.ps1 --next-bug-id "<feature_dir>"
Create or append to <feature_dir>/bugs.md using the template at bugs-template.md. [EXPLICIT]
Fill in:
reported#number if from GitHub inbound, _(none)_ otherwise_(empty until investigation)__(empty until implementation)_If bugs.md already exists, append with --- separator before the new entry. Do NOT modify existing entries. [EXPLICIT]
If bugs.md does not exist, create it with the header # Bug Reports: <feature-name> followed by the entry. [EXPLICIT]
For text-input bugs only (NOT for GitHub inbound — issue already exists): [EXPLICIT]
gh issue create --title "<description>" --body "<bugs.md entry content>" --label "bug" if gh available, otherwise curl the GitHub API (POST /repos/{owner}/{repo}/issues)Unix/macOS/Linux:
bash .tessl/tiles/tessl-labs/intent-integrity-kit/skills/iikit-core/scripts/bash/testify-tdd.sh assess-tdd "CONSTITUTION.md"
Windows (PowerShell):
pwsh .tessl/tiles/tessl-labs/intent-integrity-kit/skills/iikit-core/scripts/powershell/testify-tdd.ps1 assess-tdd "CONSTITUTION.md"
Parse JSON response for determination field. [EXPLICIT]
If TDD is mandatory (determination = mandatory): [EXPLICIT]
<feature_dir>/tests/features/ if it doesn't exist<feature_dir>/tests/features/bugfix_<BUG-NNN>.feature:
@BUG-NNN
Feature: Bug fix for BUG-NNN — <description>
Scenario: <description>
Given <conditions that trigger the bug>
When <action that causes incorrect behavior>
Then <expected correct behavior>
bash .tessl/tiles/tessl-labs/intent-integrity-kit/skills/iikit-core/scripts/bash/testify-tdd.sh rehash "<feature_dir>/tests/features"
valid, STOP and report error:
bash .tessl/tiles/tessl-labs/intent-integrity-kit/skills/iikit-core/scripts/bash/testify-tdd.sh verify-hash "<feature_dir>/tests/features"
Bug fix tasks use the T-B prefix (e.g., T-B001, T-B002) to distinguish them from regular tasks (T001, T002). This is mandatory — the dashboard and parsers rely on the T-B prefix to identify bug fix tasks and calculate implementation progress correctly.
Get next task IDs: [EXPLICIT]
Unix/macOS/Linux:
bash .tessl/tiles/tessl-labs/intent-integrity-kit/skills/iikit-core/scripts/bash/bugfix-helpers.sh --next-task-ids "<feature_dir>" <count>
Windows (PowerShell):
pwsh .tessl/tiles/tessl-labs/intent-integrity-kit/skills/iikit-core/scripts/powershell/bugfix-helpers.ps1 --next-task-ids "<feature_dir>" <count>
Non-TDD task set (count = 3):
## Bug Fix Tasks
- [ ] T-BNNN [BUG-NNN] Investigate root cause for BUG-NNN: <description>
- [ ] T-BNNN+1 [BUG-NNN] Implement fix for BUG-NNN: <description>
- [ ] T-BNNN+2 [BUG-NNN] Write regression test for BUG-NNN: <description>
TDD task set (count = 2):
## Bug Fix Tasks
- [ ] T-BNNN [BUG-NNN] Implement fix for BUG-NNN referencing test spec TS-NNN: <description>
- [ ] T-BNNN+1 [BUG-NNN] Verify fix passes test TS-NNN for BUG-NNN: <description>
If GitHub issue is linked, include reference in task descriptions (e.g., (GitHub #42)). [EXPLICIT]
Append to existing <feature_dir>/tasks.md. If tasks.md does not exist, create it with: [EXPLICIT]
# Tasks: <feature-name>
## Bug Fix Tasks
[tasks here]
Do NOT modify existing entries or task IDs in tasks.md. [EXPLICIT]
git add specs/*/bugs.md specs/*/tasks.md specs/*/tests/features/
git commit -m "bugfix: <BUG-ID> <short-description>"
Regenerate the dashboard so the pipeline reflects the new bug and tasks: [EXPLICIT]
bash .tessl/tiles/tessl-labs/intent-integrity-kit/skills/iikit-core/scripts/bash/generate-dashboard-safe.sh
Windows: pwsh .tessl/tiles/tessl-labs/intent-integrity-kit/skills/iikit-core/scripts/powershell/generate-dashboard-safe.ps1 [EXPLICIT]
Output a summary: [EXPLICIT]
Bug reported successfully! [EXPLICIT]
Bug ID: BUG-NNN
Feature: <feature-name>
Severity: <severity>
GitHub Issue: #number (or N/A)
Tasks: T-BNNN through T-BNNN+N
Files modified: [EXPLICIT]
- <feature_dir>/bugs.md (created/appended)
- <feature_dir>/tasks.md (appended)
- <feature_dir>/tests/features/bugfix_BUG-NNN.feature (created, TDD only)
Next step:
Run: bash .tessl/tiles/tessl-labs/intent-integrity-kit/skills/iikit-core/scripts/bash/next-step.sh --phase bugfix --json
Parse `next_step` (will be /iikit-07-implement) and `model_tier`.
Include `model_tier` for next_step and any alt_steps so user knows best model per option.
- <next_step> — runs in bugfix mode (relaxed gates: no checklist or plan required, traces to bugs.md instead of spec)
- Dashboard: file://$(pwd)/.specify/dashboard.html (resolve the path)
| Condition | Response |
|---|---|
| Empty input | ERROR with usage example |
| No features found | ERROR: "Run /iikit-01-specify first" |
| Feature validation failed | ERROR with specific message |
| GitHub API unreachable | Fall back: gh → curl GitHub API → skip with WARN |
| GitHub issue not found | ERROR with "verify issue number" |
| TDD required, no test artifacts | ERROR: "Run /iikit-04-testify first" |
| Existing bugs.md | Append without modifying existing entries |
| Existing tasks.md | Append without modifying existing entries |
Example invocations: [EXPLICIT]
| Scenario | Handling |
|---|---|
| Empty or minimal input | Request clarification before proceeding |
| Conflicting requirements | Flag conflicts explicitly, propose resolution |
| Out-of-scope request | Redirect to appropriate skill or escalate |
Searches, retrieves, and installs Agent Skills from prompts.chat registry using MCP tools like search_skills and get_skill. Activates for finding skills, browsing catalogs, or extending Claude.