CD postmortem
Distil the conversation we just had into a structured 7-file postmortem set under `.ralphy/workspaces/<ws>/projects/<id>/postmortem/` for the active ralphy project. Splits the record into chronological chat history, lessons learned, ralphy-CLI bug list (with the raw `bunx` / `ffmpeg` / `curl` workarounds the agent had to reach for), model-and-cost rollup, workflow / playbook fixes, and a units-produced + provenance record (the shipped Units + their template/style/recipe/asset blocks, for the extract/publish path). Use this skill whenever the user types `/postmortem`, asks for a "retro" / "lessons learned" / "what did we learn" / "write up the lessons", or says things like "write best practices", "debrief", "record what didn't work" after a non-trivial multi-iteration ralphy session. Also use proactively at the end of any ralphy session that had ≥2 user-driven course corrections (re-rolls, model swaps, scope pivots) or ≥1 CLI gap the agent worked around with raw tooling — the iteration history fades from chat memory, and a checked-in `postmortem/` set is the only durable record. Don't skip this even if the project shipped successfully — successful projects with painful iteration history are the most valuable to document.
Distil the conversation we just had into a structured 7-file postmortem set under .ralphy/workspaces/<ws>/projects/<id>/postmortem/ for the active ralphy…
As a process D 49/100 · Unfinished process — References files that are not bundled: ../memory-review/SKILL.md
How to improve
- Shorten the description to 1024 characters.
- The text references files that are not there: add them or drop the references.
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 9. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 1239 chars, limit 1024 - warning
missing-refreference to a missing file: ../memory-review/SKILL.md - note
frontmatter-keyunknown frontmatter key "namespace" - note
edit-residuethe text marks something as outdated (lines 110, 112): check that old rules are not kept next to new ones — the full check reads the text for contradictions
Process rating: all ten parameters 49/100
- 0Tools and files. 1 referenced file(s) missing: ../memory-review/SKILL.md
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 22 mutating operations with no state check
- 70When it triggers. States when to use, but not when not to
- 70Execution cost. Instruction body is 4120 tokens
- 100Steps. 71 steps
- 100Failures and branches. 1 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 13 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (6 tags): a typed call is more reliable
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 1239: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 6 example trigger phrases
- +4Structure: 14 headings
- +3Step-by-step instructions: 71 items
- +4Has examples (4 code blocks)
- +4Reference files are cited in the instructions (8 of 8)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 58.