Skills › Superpowers › diagnosing-superpowers › report.md

report.md

82 lines · skills/diagnosing-superpowers/templates/report.md at 2ce8aa1

Starts an agent Uses an outside tool

Open on GitHub

Most marks come from matching words in the file, so treat them as pointers.

1# Session diagnosis: <session-id>

3Report path: ~/.superpowers/diagnosing-superpowers/<session-id>/report.md

4Written: <ISO timestamp>

Session diagnosis: <session-id>

Report path: ~/.superpowers/diagnosing-superpowers/<session-id>/report.md Written: <ISO timestamp>

Raw lines 1 to 5

6## 1. Problem statement (REQUIRED)

8<Copied from the case file.>

1. Problem statement (REQUIRED)

Raw lines 6 to 9

10## 2. Triage verdict (REQUIRED)

12<What the evidence shows happened around the reported problem. Prose, with

13`path:line` after every claim. State confidence: high / medium / low, and

14what would raise it. No statement about what superpowers should do.>

2. Triage verdict (REQUIRED)

Raw lines 10 to 15

16## 3. Environment (REQUIRED)

18- OS:

19- Harness and version:

20- Models seen:

21- Superpowers install root / version / git sha:

22- Skill files read or injected (sha1 table from the case file):

23- Other plugins, extensions, MCP servers:

24- Instruction files present (paths only):

26Label every environment field and skill observation as historical evidence,

27unverified snapshot, current observation, or unknown, and record its

28supporting evidence location.

3. Environment (REQUIRED)

OS:
Harness and version:
Models seen:
Superpowers install root / version / git sha:
Skill files read or injected (sha1 table from the case file):
Other plugins, extensions, MCP servers:
Instruction files present (paths only):

Label every environment field and skill observation as historical evidence, unverified snapshot, current observation, or unknown, and record its supporting evidence location.

Raw lines 16 to 29

Uses an outside tool MCP :23

30## 4. Sessions examined (REQUIRED)

33|---|---|---|---|---|

35Rejected candidates: <id — path — why>, or "none".

4. Sessions examined (REQUIRED)

Role	Session id	Absolute path	Lines	Bytes

Rejected candidates: <id — path — why>, or "none".

Raw lines 30 to 36

37## 5. Timeline (REQUIRED)

39One row per human-typed prompt. Events column lists skills invoked,

40subagents dispatched, compaction, errors, resumes, aborts.

43|---|---|---|---|---|

5. Timeline (REQUIRED)

One row per human-typed prompt. Events column lists skills invoked, subagents dispatched, compaction, errors, resumes, aborts.

Turn	Line	Time	Request (one line)	Events

Raw lines 37 to 44

Starts an agent subagents :40

Starts an agent dispatched :40

45## 6. Findings (REQUIRED, one subsection per dimension)

47Each finding:

48```

49- finding: <one sentence>

50 evidence: <path:line> — "<short quote>"

51 turns: <first>–<last>

52 confidence: high | medium | low

53```

54A dimension with nothing to report says `none found — checked: <what was checked>`.

6. Findings (REQUIRED, one subsection per dimension)

Each finding:

- finding: <one sentence>
  evidence: <path:line> — "<short quote>"
  turns: <first>–<last>
  confidence: high | medium | low

A dimension with nothing to report says none found — checked: <what was checked>.

Raw lines 45 to 55

56### 6.1 Skill timeline

6.1 Skill timeline

Raw lines 56 to 56

57### 6.2 Plan adherence

6.2 Plan adherence

Raw lines 57 to 57

58### 6.3 Repeated work

6.3 Repeated work

Raw lines 58 to 58

59### 6.4 Stumbles

6.4 Stumbles

Raw lines 59 to 59

60### 6.5 Quality evidence

6.5 Quality evidence

Raw lines 60 to 60

61### 6.6 Request conflicts

6.6 Request conflicts

Raw lines 61 to 61

62### 6.7 Cost and time

6.7 Cost and time

Raw lines 62 to 62

63### 6.8 Other plugins and skills used

6.8 Other plugins and skills used

Raw lines 63 to 64

65## 7. Superpowers involvement (REQUIRED)

67not indicated | possible | likely

69Evidence lines: <path:line list>. This section states involvement only. It

70does not name a defect and does not propose a change.

7. Superpowers involvement (REQUIRED)

not indicated | possible | likely

Evidence lines: <path:line list>. This section states involvement only. It does not name a defect and does not propose a change.

Raw lines 65 to 71

72## 8. Coverage notes (REQUIRED)

74- Not read: <ranges, files, and why>

75- Harness features unavailable: <list or none>

76- Session was in progress at read time: yes/no

77- For your human partner to double-check: <list or none>

8. Coverage notes (REQUIRED)

Not read: <ranges, files, and why>
Harness features unavailable: <list or none>
Session was in progress at read time: yes/no
For your human partner to double-check: <list or none>

Raw lines 72 to 78

79## 9. Similar sessions (only when requested)

82|---|---|---|---|---|---|

9. Similar sessions (only when requested)

Session id	Path	Date	Harness	Matched	Did not match

Raw lines 79 to 82