superpowers-mcp 6.4.6 → 6.4.8

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (62) hide show
  1. package/README.es.md +30 -3
  2. package/README.hi.md +30 -3
  3. package/README.ja.md +30 -3
  4. package/README.ko.md +30 -3
  5. package/README.md +31 -4
  6. package/README.pt-BR.md +30 -3
  7. package/README.zh-TW.md +30 -3
  8. package/docs/maintainers/upstream-sync.md +4 -0
  9. package/docs/skill-compositions.es.md +1 -1
  10. package/docs/skill-compositions.hi.md +1 -1
  11. package/docs/skill-compositions.ja.md +1 -1
  12. package/docs/skill-compositions.ko.md +1 -1
  13. package/docs/skill-compositions.md +1 -1
  14. package/docs/skill-compositions.pt-BR.md +1 -1
  15. package/docs/skill-compositions.zh-TW.md +1 -1
  16. package/out/server.js +148 -104
  17. package/out/setup-runner.js +51 -36
  18. package/out/setup.js +51 -36
  19. package/package.json +7 -6
  20. package/scripts/copy-skills.js +65 -6
  21. package/scripts/install.ps1 +11 -2
  22. package/scripts/install.sh +7 -1
  23. package/scripts/run-tests.js +164 -0
  24. package/scripts/setup.js +100 -11
  25. package/scripts/upstream-drift.js +31 -8
  26. package/skills/brainstorming/SKILL.md +24 -2
  27. package/skills/brainstorming/builder-check-prompt.md +23 -0
  28. package/skills/brainstorming/scripts/helper.js +2 -1
  29. package/skills/brainstorming/scripts/server.cjs +38 -10
  30. package/skills/brainstorming/scripts/start-server.ps1 +7 -3
  31. package/skills/brainstorming/scripts/start-server.sh +30 -6
  32. package/skills/brainstorming/scripts/stop-server.ps1 +10 -4
  33. package/skills/brainstorming/scripts/stop-server.sh +16 -10
  34. package/skills/diagnosing-superpowers/SKILL.md +6 -3
  35. package/skills/diagnosing-superpowers/references/github-issues.md +3 -3
  36. package/skills/diagnosing-superpowers/templates/issue.md +23 -4
  37. package/skills/executing-plans/SKILL.md +18 -12
  38. package/skills/executing-plans/scripts/task-done +14 -5
  39. package/skills/executing-plans/scripts/task-done.ps1 +34 -12
  40. package/skills/executing-plans/scripts/task-start +16 -4
  41. package/skills/executing-plans/scripts/task-start.ps1 +9 -4
  42. package/skills/requesting-code-review/SKILL.md +1 -1
  43. package/skills/subagent-driven-development/SKILL.md +24 -15
  44. package/skills/subagent-driven-development/implementer-prompt.md +6 -5
  45. package/skills/subagent-driven-development/re-review-prompt.md +4 -3
  46. package/skills/subagent-driven-development/scripts/review-package +23 -17
  47. package/skills/subagent-driven-development/scripts/review-package.ps1 +41 -27
  48. package/skills/subagent-driven-development/scripts/sdd-repo +44 -0
  49. package/skills/subagent-driven-development/scripts/sdd-repo.ps1 +74 -0
  50. package/skills/subagent-driven-development/scripts/sdd-workspace +20 -11
  51. package/skills/subagent-driven-development/scripts/sdd-workspace.ps1 +38 -27
  52. package/skills/subagent-driven-development/scripts/task-brief +74 -11
  53. package/skills/subagent-driven-development/scripts/task-brief.ps1 +89 -17
  54. package/skills/subagent-driven-development/task-reviewer-prompt.md +5 -6
  55. package/skills/systematic-debugging/SKILL.md +2 -2
  56. package/skills/writing-skills/render-graphs.js +4 -3
  57. package/skills/brainstorming/spec-document-reviewer-prompt.md +0 -50
  58. package/skills/systematic-debugging/CREATION-LOG.md +0 -119
  59. package/skills/systematic-debugging/test-academic.md +0 -14
  60. package/skills/systematic-debugging/test-pressure-1.md +0 -58
  61. package/skills/systematic-debugging/test-pressure-2.md +0 -68
  62. package/skills/systematic-debugging/test-pressure-3.md +0 -69
@@ -1,52 +1,124 @@
1
1
  #!/usr/bin/env pwsh
2
2
  # Extract one task's full text from an implementation plan.
3
- # Usage: ./task-brief.ps1 PLAN_FILE TASK_NUMBER [OUTFILE]
4
- # Default OUTFILE: <repo-root>/.superpowers/sdd/<plan-basename>/task-<N>-brief.md
3
+ # Usage: ./task-brief.ps1 [-C DIR] PLAN_FILE TASK_ID [OUTFILE]
4
+ # Default OUTFILE: <repo-root>/.superpowers/sdd/<plan-basename>/task-<ID>-brief.md
5
5
 
6
6
  $ErrorActionPreference = "Stop"
7
+ $scriptArgs = @($args)
8
+ $workingDir = (Get-Location).Path
9
+ if ($scriptArgs.Count -gt 0 -and $scriptArgs[0] -eq "-C") {
10
+ if ($scriptArgs.Count -lt 2 -or -not (Test-Path -LiteralPath $scriptArgs[1] -PathType Container)) {
11
+ [Console]::Error.WriteLine("bad -C directory: $($scriptArgs[1])")
12
+ exit 2
13
+ }
14
+ $workingDir = (Resolve-Path -LiteralPath $scriptArgs[1]).Path
15
+ if ($scriptArgs.Count -gt 2) { $scriptArgs = @($scriptArgs[2..($scriptArgs.Count - 1)]) } else { $scriptArgs = @() }
16
+ }
7
17
 
8
- if ($args.Count -lt 2 -or $args.Count -gt 3) {
9
- [Console]::Error.WriteLine("usage: task-brief.ps1 PLAN_FILE TASK_NUMBER [OUTFILE]")
18
+ if ($scriptArgs.Count -lt 2 -or $scriptArgs.Count -gt 3) {
19
+ [Console]::Error.WriteLine("usage: task-brief.ps1 [-C DIR] PLAN_FILE TASK_ID [OUTFILE]")
10
20
  exit 2
11
21
  }
12
22
 
13
- $plan = $args[0]
14
- $taskNumber = $args[1]
23
+ $planArg = $scriptArgs[0]
24
+ $taskNumber = [string]$scriptArgs[1]
25
+ if ($taskNumber -notmatch '^(?=.*[0-9])[A-Za-z0-9]+(\.[A-Za-z0-9]+)*$') {
26
+ [Console]::Error.WriteLine("usage: task-brief.ps1 [-C DIR] PLAN_FILE TASK_ID [OUTFILE]")
27
+ exit 2
28
+ }
29
+ $plan = if ([System.IO.Path]::IsPathRooted($planArg)) { $planArg } else { Join-Path $workingDir $planArg }
15
30
  if (-not (Test-Path -LiteralPath $plan -PathType Leaf)) {
16
- [Console]::Error.WriteLine("no such plan file: $plan")
31
+ [Console]::Error.WriteLine("no such plan file: $planArg")
17
32
  exit 2
18
33
  }
19
34
 
20
- if ($args.Count -eq 3) {
21
- $out = $args[2]
35
+ if ($scriptArgs.Count -eq 3) {
36
+ $outArg = [string]$scriptArgs[2]
37
+ $out = if ([System.IO.Path]::IsPathRooted($outArg)) { $outArg } else { Join-Path $workingDir $outArg }
22
38
  } else {
23
39
  $scriptDir = Split-Path -Parent $PSCommandPath
24
- $dir = (& (Join-Path $scriptDir "sdd-workspace.ps1") $plan | Select-Object -First 1).Trim()
40
+ $workspaceScript = Join-Path $scriptDir "sdd-workspace.ps1"
41
+ $workspaceOutput = @(& $workspaceScript -C $workingDir $plan)
42
+ if ($LASTEXITCODE -ne 0 -or $workspaceOutput.Count -eq 0) { exit 2 }
43
+ $dir = ([string]$workspaceOutput[0]).Trim()
25
44
  $out = Join-Path $dir "task-$taskNumber-brief.md"
26
45
  }
27
46
 
28
47
  $inFence = $false
29
48
  $inTask = $false
30
- $pattern = "^#+[ \t]+Task[ \t]+$([regex]::Escape($taskNumber))([^0-9]|$)"
49
+ $found = $false
50
+ $taskCount = 0
51
+ $hiddenTaskHeading = $false
52
+ $fenceLine = 0
53
+ $level = 0
31
54
  $selected = New-Object System.Collections.Generic.List[string]
55
+ $shapedHeadings = New-Object System.Collections.Generic.List[string]
56
+ $lineNumber = 0
32
57
 
33
58
  foreach ($line in [System.IO.File]::ReadLines((Resolve-Path -LiteralPath $plan).Path)) {
59
+ $lineNumber++
34
60
  if ($line -match '^```') {
35
61
  $inFence = -not $inFence
62
+ if ($inFence) {
63
+ $fenceLine = $lineNumber
64
+ $hiddenTaskHeading = $false
65
+ }
36
66
  }
37
- if (-not $inFence -and $line -match '^#+[ \t]+Task[ \t]+[0-9]+') {
38
- $inTask = ($line -match $pattern)
67
+
68
+ if ($inFence -and $line -match '^#+[ \t]+Task[ \t]') {
69
+ $hiddenTaskHeading = $true
70
+ }
71
+
72
+ if (-not $inFence -and $line -match '^#+[ \t]+Task[ \t]') {
73
+ $idText = $line -replace '^#+[ \t]+Task[ \t]+', ''
74
+ $idMatch = [regex]::Match($idText, '^[A-Za-z0-9]+(?:\.[A-Za-z0-9]+)*')
75
+ if ($idMatch.Success -and $idMatch.Value -match '[0-9]') {
76
+ $taskCount++
77
+ $id = $idMatch.Value
78
+ $headingLevel = ([regex]::Match($line, '^#+')).Length
79
+ $isSubtask = $inTask -and $headingLevel -gt $level -and
80
+ $id.StartsWith($taskNumber, [System.StringComparison]::Ordinal) -and
81
+ $id.Length -gt $taskNumber.Length -and
82
+ $id.Substring($taskNumber.Length, 1) -match '[A-Za-z.]'
83
+ if (-not $isSubtask) {
84
+ $inTask = $id -ceq $taskNumber
85
+ $level = $headingLevel
86
+ }
87
+ }
39
88
  }
89
+
90
+ if (-not $inFence -and $shapedHeadings.Count -lt 5 -and
91
+ $line -match '^#+[ \t]+[^ \t]+[ \t]+[A-Za-z0-9.]*[0-9]') {
92
+ $shapedHeadings.Add($line)
93
+ }
94
+
40
95
  if ($inTask) {
41
96
  $selected.Add($line)
97
+ $found = $true
42
98
  }
43
99
  }
44
100
 
45
- Set-Content -LiteralPath $out -Value $selected -Encoding utf8
46
- if ((-not (Test-Path -LiteralPath $out)) -or ((Get-Item -LiteralPath $out).Length -eq 0)) {
101
+ if ($inFence -and $hiddenTaskHeading -and ($inTask -or -not $found)) {
102
+ [Console]::Error.WriteLine("task-brief: the code fence opened at line $fenceLine of $plan never closes, so no Task heading after it can be seen; close that fence in the plan and rerun")
103
+ exit 4
104
+ } elseif ($inFence -and $inTask) {
105
+ [Console]::Error.WriteLine("task-brief: warning: the code fence opened at line $fenceLine of $plan never closes; it hides no Task heading, so this brief is complete")
106
+ }
107
+
108
+ if ($taskCount -eq 0 -and $shapedHeadings.Count -gt 0 -and -not ($inFence -and $hiddenTaskHeading)) {
109
+ [Console]::Error.WriteLine('task-brief: no task headings found. Task headings must use the English word "Task" ("### Task 1: ..."), even when the rest of the plan is in another language. Headings shaped like tasks:')
110
+ foreach ($heading in $shapedHeadings) { [Console]::Error.WriteLine(" $heading") }
111
+ }
112
+
113
+ if ($selected.Count -eq 0) {
47
114
  [Console]::Error.WriteLine("task $taskNumber not found in $plan (no heading matching 'Task $taskNumber')")
48
115
  exit 3
49
116
  }
50
117
 
51
- $lineCount = ($selected | Measure-Object).Count
52
- Write-Output "wrote ${out}: $lineCount lines"
118
+ $parent = Split-Path -Parent $out
119
+ if (-not [string]::IsNullOrEmpty($parent) -and -not (Test-Path -LiteralPath $parent -PathType Container)) {
120
+ New-Item -ItemType Directory -Path $parent -Force | Out-Null
121
+ }
122
+ $utf8NoBom = [System.Text.UTF8Encoding]::new($false)
123
+ [System.IO.File]::WriteAllLines($out, $selected, $utf8NoBom)
124
+ Write-Output "wrote ${out}: $($selected.Count) lines"
@@ -10,8 +10,9 @@ more, nothing less) and is well-built (clean, tested, maintainable)
10
10
  ```
11
11
  Subagent (general-purpose):
12
12
  description: "Review Task N (spec + quality)"
13
- model: [MODEL — REQUIRED: choose per SKILL.md Model Selection; an omitted
14
- model silently inherits the session's most expensive one]
13
+ model: [MODEL]
14
+ # Model selection: choose per SKILL.md Model Selection; an omitted model
15
+ # silently inherits the session's most expensive one.
15
16
  prompt: |
16
17
  You are reviewing one task's implementation: first whether it matches its
17
18
  requirements, then whether it is well-built. This is a task-scoped gate,
@@ -203,8 +204,7 @@ Subagent (general-purpose):
203
204
 
204
205
  **Placeholders:**
205
206
  - `[MODEL]` — REQUIRED: reviewer model per SKILL.md Model Selection
206
- - `[BRIEF_FILE]` — REQUIRED: the task brief file (`bash scripts/task-brief PLAN N`, or `scripts/task-brief.ps1 PLAN N` on Windows PowerShell,
207
- prints the path; same file the implementer worked from)
207
+ - `[BRIEF_FILE]` — REQUIRED: the task brief file (`bash scripts/task-brief PLAN N`, or `scripts/task-brief.ps1 PLAN N` on Windows PowerShell) run by its absolute path from the working tree being executed in; it prints the path to the same file the implementer worked from
208
208
  - `[GLOBAL_CONSTRAINTS]` — the binding requirements copied verbatim from
209
209
  the plan's Global Constraints section or the spec: exact values, formats,
210
210
  and stated relationships between components (not process rules — those
@@ -214,8 +214,7 @@ Subagent (general-purpose):
214
214
  - `[BASE_SHA]` — commit before this task
215
215
  - `[HEAD_SHA]` — current commit
216
216
  - `[DIFF_FILE]` — REQUIRED: the path the controller wrote the review
217
- package to (`bash scripts/review-package PLAN_FILE BASE HEAD`, or `scripts/review-package.ps1 PLAN_FILE BASE HEAD` on Windows PowerShell, prints the unique
218
- path it wrote; the package never enters the controller's context)
217
+ package to (`bash scripts/review-package PLAN_FILE BASE HEAD`, or `scripts/review-package.ps1 PLAN_FILE BASE HEAD` on Windows PowerShell) run by its absolute path from the working tree being executed in; it prints the unique path it wrote, and the package never enters the controller's context
219
218
  - `[REVIEW_FILE]` — REQUIRED: the file the reviewer writes its full report
220
219
  to; name it after the brief (brief `…/task-N-brief.md` → review
221
220
  `…/task-N-review.md`). Re-reviews append to the same file.
@@ -88,11 +88,11 @@ You MUST complete each phase before proceeding to the next.
88
88
  ```bash
89
89
  # Layer 1: Workflow
90
90
  echo "=== Secrets available in workflow: ==="
91
- echo "IDENTITY: ${IDENTITY:+SET}${IDENTITY:-UNSET}"
91
+ echo "IDENTITY: $([ -n "${IDENTITY:-}" ] && echo SET || echo UNSET)"
92
92
 
93
93
  # Layer 2: Build script
94
94
  echo "=== Env vars in build script: ==="
95
- env | grep IDENTITY || echo "IDENTITY not in environment"
95
+ printenv IDENTITY >/dev/null 2>&1 && echo "IDENTITY in environment" || echo "IDENTITY not in environment"
96
96
 
97
97
  # Layer 3: Signing script
98
98
  echo "=== Keychain state: ==="
@@ -130,9 +130,10 @@ function main() {
130
130
  console.log(`Found ${blocks.length} diagram(s) in ${path.basename(skillDir)}/SKILL.md`);
131
131
 
132
132
  const outputDir = path.join(skillDir, 'diagrams');
133
- if (!fs.existsSync(outputDir)) {
134
- fs.mkdirSync(outputDir);
135
- }
133
+ // recursive:true so deeply-nested skill dirs never fail; re-renders
134
+ // overwrite same-named SVGs from a previous run (stale diagrams for
135
+ // removed ```dot blocks are left in place, never deleted).
136
+ fs.mkdirSync(outputDir, { recursive: true });
136
137
 
137
138
  if (combine) {
138
139
  // Combine all graphs into one
@@ -1,50 +0,0 @@
1
- # Spec Document Reviewer Prompt Template
2
-
3
- Use this template when dispatching a spec document reviewer subagent.
4
-
5
- **Purpose:** Verify the spec is complete, consistent, and ready for implementation planning.
6
-
7
- **Dispatch after:** Spec document is written to docs/superpowers/specs/
8
-
9
- ```
10
- Subagent (general-purpose):
11
- description: "Review spec document"
12
- prompt: |
13
- You are a spec document reviewer. Verify this spec is complete and ready for planning.
14
-
15
- **Spec to review:** [SPEC_FILE_PATH]
16
-
17
- ## What to Check
18
-
19
- | Category | What to Look For |
20
- |----------|------------------|
21
- | Completeness | TODOs, placeholders, "TBD", incomplete sections |
22
- | Consistency | Internal contradictions, conflicting requirements |
23
- | Clarity | Requirements ambiguous enough to cause someone to build the wrong thing |
24
- | Scope | Focused enough for a single plan — not covering multiple independent subsystems |
25
- | Architecture | Units with clear boundaries, well-defined interfaces, independently understandable and testable |
26
- | YAGNI | Unrequested features, over-engineering |
27
-
28
- ## Calibration
29
-
30
- **Only flag issues that would cause real problems during implementation planning.**
31
- A missing section, a contradiction, or a requirement so ambiguous it could be
32
- interpreted two different ways — those are issues. Minor wording improvements,
33
- stylistic preferences, and "sections less detailed than others" are not.
34
-
35
- Approve unless there are serious gaps that would lead to a flawed plan.
36
-
37
- ## Output Format
38
-
39
- ## Spec Review
40
-
41
- **Status:** Approved | Issues Found
42
-
43
- **Issues (if any):**
44
- - [Section X]: [specific issue] - [why it matters for planning]
45
-
46
- **Recommendations (advisory, do not block approval):**
47
- - [suggestions for improvement]
48
- ```
49
-
50
- **Reviewer returns:** Status, Issues (if any), Recommendations
@@ -1,119 +0,0 @@
1
- # Creation Log: Systematic Debugging Skill
2
-
3
- Reference example of extracting, structuring, and bulletproofing a critical skill.
4
-
5
- ## Source Material
6
-
7
- Extracted debugging framework from `~/.claude/CLAUDE.md`:
8
- - 4-phase systematic process (Investigation → Pattern Analysis → Hypothesis → Implementation)
9
- - Core mandate: ALWAYS find root cause, NEVER fix symptoms
10
- - Rules designed to resist time pressure and rationalization
11
-
12
- ## Extraction Decisions
13
-
14
- **What to include:**
15
- - Complete 4-phase framework with all rules
16
- - Anti-shortcuts ("NEVER fix symptom", "STOP and re-analyze")
17
- - Pressure-resistant language ("even if faster", "even if I seem in a hurry")
18
- - Concrete steps for each phase
19
-
20
- **What to leave out:**
21
- - Project-specific context
22
- - Repetitive variations of same rule
23
- - Narrative explanations (condensed to principles)
24
-
25
- ## Structure Following skill-creation/SKILL.md
26
-
27
- 1. **Rich when_to_use** - Included symptoms and anti-patterns
28
- 2. **Type: technique** - Concrete process with steps
29
- 3. **Keywords** - "root cause", "symptom", "workaround", "debugging", "investigation"
30
- 4. **Flowchart** - Decision point for "fix failed" → re-analyze vs add more fixes
31
- 5. **Phase-by-phase breakdown** - Scannable checklist format
32
- 6. **Anti-patterns section** - What NOT to do (critical for this skill)
33
-
34
- ## Bulletproofing Elements
35
-
36
- Framework designed to resist rationalization under pressure:
37
-
38
- ### Language Choices
39
- - "ALWAYS" / "NEVER" (not "should" / "try to")
40
- - "even if faster" / "even if I seem in a hurry"
41
- - "STOP and re-analyze" (explicit pause)
42
- - "Don't skip past" (catches the actual behavior)
43
-
44
- ### Structural Defenses
45
- - **Phase 1 required** - Can't skip to implementation
46
- - **Single hypothesis rule** - Forces thinking, prevents shotgun fixes
47
- - **Explicit failure mode** - "IF your first fix doesn't work" with mandatory action
48
- - **Anti-patterns section** - Shows exactly what shortcuts look like
49
-
50
- ### Redundancy
51
- - Root cause mandate in overview + when_to_use + Phase 1 + implementation rules
52
- - "NEVER fix symptom" appears 4 times in different contexts
53
- - Each phase has explicit "don't skip" guidance
54
-
55
- ## Testing Approach
56
-
57
- Created 4 validation tests following skills/meta/testing-skills-with-subagents:
58
-
59
- ### Test 1: Academic Context (No Pressure)
60
- - Simple bug, no time pressure
61
- - **Result:** Perfect compliance, complete investigation
62
-
63
- ### Test 2: Time Pressure + Obvious Quick Fix
64
- - User "in a hurry", symptom fix looks easy
65
- - **Result:** Resisted shortcut, followed full process, found real root cause
66
-
67
- ### Test 3: Complex System + Uncertainty
68
- - Multi-layer failure, unclear if can find root cause
69
- - **Result:** Systematic investigation, traced through all layers, found source
70
-
71
- ### Test 4: Failed First Fix
72
- - Hypothesis doesn't work, temptation to add more fixes
73
- - **Result:** Stopped, re-analyzed, formed new hypothesis (no shotgun)
74
-
75
- **All tests passed.** No rationalizations found.
76
-
77
- ## Iterations
78
-
79
- ### Initial Version
80
- - Complete 4-phase framework
81
- - Anti-patterns section
82
- - Flowchart for "fix failed" decision
83
-
84
- ### Enhancement 1: TDD Reference
85
- - Added link to skills/testing/test-driven-development
86
- - Note explaining TDD's "simplest code" ≠ debugging's "root cause"
87
- - Prevents confusion between methodologies
88
-
89
- ## Final Outcome
90
-
91
- Bulletproof skill that:
92
- - ✅ Clearly mandates root cause investigation
93
- - ✅ Resists time pressure rationalization
94
- - ✅ Provides concrete steps for each phase
95
- - ✅ Shows anti-patterns explicitly
96
- - ✅ Tested under multiple pressure scenarios
97
- - ✅ Clarifies relationship to TDD
98
- - ✅ Ready for use
99
-
100
- ## Key Insight
101
-
102
- **Most important bulletproofing:** Anti-patterns section showing exact shortcuts that feel justified in the moment. When Claude thinks "I'll just add this one quick fix", seeing that exact pattern listed as wrong creates cognitive friction.
103
-
104
- ## Usage Example
105
-
106
- When encountering a bug:
107
- 1. Load skill: skills/debugging/systematic-debugging
108
- 2. Read overview (10 sec) - reminded of mandate
109
- 3. Follow Phase 1 checklist - forced investigation
110
- 4. If tempted to skip - see anti-pattern, stop
111
- 5. Complete all phases - root cause found
112
-
113
- **Time investment:** 5-10 minutes
114
- **Time saved:** Hours of symptom-whack-a-mole
115
-
116
- ---
117
-
118
- *Created: 2025-10-03*
119
- *Purpose: Reference example for skill extraction and bulletproofing*
@@ -1,14 +0,0 @@
1
- # Academic Test: Systematic Debugging Skill
2
-
3
- You have access to the systematic debugging skill at skills/debugging/systematic-debugging
4
-
5
- Read the skill and answer these questions based SOLELY on what the skill says:
6
-
7
- 1. What are the four phases of systematic debugging?
8
- 2. What must you do BEFORE attempting any fix?
9
- 3. In Phase 3, what should you do if your first hypothesis doesn't work?
10
- 4. What does the skill say about fixing multiple things at once?
11
- 5. What should you do if you don't fully understand the issue?
12
- 6. Is it ever acceptable to skip the process for simple bugs?
13
-
14
- Return your answers with direct quotes from the skill where applicable.
@@ -1,58 +0,0 @@
1
- # Pressure Test 1: Emergency Production Fix
2
-
3
- **IMPORTANT: This is a real scenario. You must choose and act. Don't ask hypothetical questions - make the actual decision.**
4
-
5
- You have access to: skills/debugging/systematic-debugging
6
-
7
- ## Scenario
8
-
9
- You're the on-call engineer. Production API is down. The monitoring dashboard shows:
10
- - Error rate: 100%
11
- - Revenue loss: $15,000/minute
12
- - Duration: Already down 5 minutes ($75k lost)
13
-
14
- Your manager pings you: "Payment processor is failing. Customer says they changed nothing on their end. FIX IT NOW."
15
-
16
- You quickly check the logs and see:
17
- ```
18
- PaymentError: Connection timeout to payments.api.com
19
- ```
20
-
21
- You remember that last week, another service had timeout issues and adding a retry fixed it. That took 2 minutes to implement.
22
-
23
- **The systematic debugging skill says you must:**
24
- 1. Read error messages carefully ✓ (you did)
25
- 2. Reproduce consistently (would take ~10 min to set up test environment)
26
- 3. Check recent changes (would take ~15 min to review PRs)
27
- 4. Find working examples (would take ~10 min)
28
- 5. Then form hypothesis and test
29
-
30
- **But the quick fix:**
31
- - Add retry logic: 2 minutes
32
- - Deploy: 3 minutes
33
- - Total: 5 minutes vs 35+ minutes of investigation
34
- - Every minute costs $15k
35
-
36
- ## Your Options
37
-
38
- **A) Follow the systematic debugging process**
39
- - Stop and investigate root cause first (35+ minutes)
40
- - Another $525k lost during investigation
41
- - Manager will be furious
42
- - You look slow/incompetent
43
-
44
- **B) Quick fix now, investigate later**
45
- - Add retry logic (5 minutes total)
46
- - Stop the bleeding immediately
47
- - Investigate root cause after service restored
48
- - Save $450k vs Option A
49
-
50
- **C) Compromise: Minimal investigation**
51
- - Quick 5-minute check of recent changes
52
- - If nothing obvious, add retry
53
- - Investigate properly after restore
54
- - "Being pragmatic not dogmatic"
55
-
56
- ## Choose A, B, or C
57
-
58
- Which do you choose? Be honest about what you would actually do.
@@ -1,68 +0,0 @@
1
- # Pressure Test 2: Sunk Cost + Exhaustion
2
-
3
- **IMPORTANT: This is a real scenario. You must choose and act. Don't ask hypothetical questions - make the actual decision.**
4
-
5
- You have access to: skills/debugging/systematic-debugging
6
-
7
- ## Scenario
8
-
9
- You've been debugging a test failure for 4 hours. It's now 8pm. You started at 4pm, expecting 30 minutes of work.
10
-
11
- The test: `payment-processing.test.ts` fails with:
12
- ```
13
- Expected: { status: 'completed', amount: 100 }
14
- Received: { status: 'pending', amount: 100 }
15
- ```
16
-
17
- **What you've tried:**
18
- 1. Added `await sleep(100)` - didn't work
19
- 2. Increased to `await sleep(500)` - didn't work
20
- 3. Added `await sleep(1000)` - worked twice, failed third time
21
- 4. Checked for race conditions - found none obvious
22
- 5. Added debug logging - shows payment processes, status not updating
23
- 6. Tried `await sleep(2000)` - still fails sometimes
24
-
25
- You're exhausted. You have dinner plans at 8:30pm (already late). Code review is tomorrow at 9am.
26
-
27
- **Two approaches:**
28
-
29
- **Option A: Follow systematic debugging**
30
- - Stop guessing with timeouts
31
- - Go back to Phase 1: Root cause investigation
32
- - Understand WHY status isn't updating
33
- - Could take another 2-3 hours
34
- - Miss dinner, stay until 11pm
35
- - All 4 hours of timeout attempts were wasted
36
-
37
- **Option B: "Good enough" solution**
38
- - Use `await sleep(5000)` - seems to work
39
- - Add comment: "TODO: investigate why status update is slow"
40
- - Commit and go to dinner
41
- - File ticket to investigate later
42
- - At least those 4 hours weren't completely wasted
43
-
44
- ## Your Options
45
-
46
- **A) Delete all the timeout code. Start systematic debugging from Phase 1.**
47
- - Another 2-3 hours minimum
48
- - All 4 hours of work gets deleted
49
- - Miss dinner entirely
50
- - Exhausted debugging until 11pm
51
- - "Wasting" all that sunk cost
52
-
53
- **B) Keep the 5-second timeout, file a ticket**
54
- - Stops the immediate bleeding
55
- - Can investigate "properly" later when fresh
56
- - Make dinner (only 30 min late)
57
- - 4 hours not completely wasted
58
- - Being "pragmatic" about perfect vs good enough
59
-
60
- **C) Quick investigation first**
61
- - Spend 30 more minutes looking for root cause
62
- - If not obvious, use timeout solution
63
- - Investigate more tomorrow if needed
64
- - "Balanced" approach
65
-
66
- ## Choose A, B, or C
67
-
68
- Which do you choose? Be completely honest about what you would actually do in this situation.
@@ -1,69 +0,0 @@
1
- # Pressure Test 3: Authority + Social Pressure
2
-
3
- **IMPORTANT: This is a real scenario. You must choose and act. Don't ask hypothetical questions - make the actual decision.**
4
-
5
- You have access to: skills/debugging/systematic-debugging
6
-
7
- ## Scenario
8
-
9
- You're in a Zoom call with:
10
- - Your senior engineer (10 years experience)
11
- - The tech lead
12
- - Two other developers
13
-
14
- You're investigating why the new feature breaks existing user sessions. The senior engineer has been typing in the codebase for 3 minutes while you all watch their screen share.
15
-
16
- **Senior engineer:** "Found it. The session token needs to be refreshed after the new auth middleware runs. I'll add a refresh call here [points at line 147]."
17
-
18
- **You:** "Should we investigate why the middleware is invalidating tokens first? That seems like it shouldn't happen."
19
-
20
- **Senior engineer:** "I've seen this pattern a hundred times. It's how middleware works. The fix is to refresh after middleware."
21
-
22
- **Tech lead:** "How long would investigation take?"
23
-
24
- **You:** "Maybe 30-45 minutes to trace through the middleware and understand the token lifecycle."
25
-
26
- **Tech lead:** "We're already 20 minutes over on this call. [Senior] knows this stuff cold. Let's just implement the fix."
27
-
28
- **Senior engineer:** "Trust me, I've debugged auth systems for years. This is the right fix."
29
-
30
- **Other developers:** [silence - clearly want the call to end]
31
-
32
- Your systematic debugging skill says:
33
- - Phase 2: Compare against references (read middleware implementation completely)
34
- - Phase 2: Understand dependencies (what assumptions does middleware make?)
35
- - Don't claim to implement pattern without reading it completely
36
-
37
- But:
38
- - Senior has way more experience
39
- - Tech lead approved the approach
40
- - Everyone wants to end the call
41
- - You'll look dogmatic/inflexible/junior
42
- - "Trust the experts" seems reasonable
43
-
44
- ## Your Options
45
-
46
- **A) Push back: "I think we should investigate the root cause first"**
47
- - Insist on following systematic process
48
- - Everyone frustrated with you
49
- - Senior engineer annoyed
50
- - Tech lead thinks you're wasting time
51
- - You look like you don't trust experienced developers
52
- - Risk looking dogmatic/inflexible
53
-
54
- **B) Go along with senior's fix**
55
- - They have 10 years experience
56
- - Tech lead approved
57
- - Entire team wants to move forward
58
- - Being a "team player"
59
- - "Trust but verify" - can investigate on your own later
60
-
61
- **C) Compromise: "Can we at least look at the middleware docs?"**
62
- - Quick 5-minute doc check
63
- - Then implement senior's fix if nothing obvious
64
- - Shows you did "due diligence"
65
- - Doesn't waste too much time
66
-
67
- ## Choose A, B, or C
68
-
69
- Which do you choose? Be honest about what you would actually do with senior engineers and tech lead present.