printing-press-output-review

Name: printing-press-output-review
Author: mvanhorn

4.6kinstalls453forks

How to install printing-press-output-review?

mvanhorn/cli-printing-press/printing-press-output-review

$npx -y skills add mvanhorn/cli-printing-press --skill printing-press-output-review

Installs into the current project.

Summary

Internal sub-skill: agentic review of a printed CLI's sampled command output for plausibility issues that rule-based checks can't encode (substring-match relevance, format bugs, silent source drops, ranking failures). Invoked via the Skill tool by main printing-press SKILL.md (Ph

Files · 1

View on GitHub

SKILL.md

1	# printing-press-output-review (internal)
2
3	Review the sampled outputs from a printed CLI for plausibility bugs that dogfood, verify, and the rule-based `scorecard --live-check` rules can't catch. Wave B policy: all findings surface as warnings, never errors.
4
5	This skill is internal-only (`user-invocable: false`). It's invoked by parents — main printing-press skill at shipcheck Phase 4.85, polish skill during its diagnostic loop. Running it standalone would produce floating findings text with no ship verdict, no fixes applied, no publish offer; the actionable wrappers are `/printing-press` and `/printing-press-polish`. The skill carries `context: fork` so the reviewer agent's diagnostic chatter stays isolated from the calling skill's context.
6
7	## Input
8
9	The caller passes `$CLI_DIR` as the argument: an absolute path to the printed CLI's working directory.
10
11	## What this catches
12
13	Bugs that rule-based checks miss, typically surfaced by 5 minutes of hands-on testing but slipping past dogfood, verify, and `scorecard --live-check` rules:
14
15	- Substring-match results that coincidentally contain the query but don't match semantically (e.g., a query matches a substring of a larger unrelated term)
16	- Aggregation commands silently dropping sources when only some of the requested N come back
17	- Ranking or sort commands returning top-N results that aren't plausibly the best for the query (broken weights, extractor fallbacks)
18	- URLs in output pointing at category index pages, feed endpoints, or random-selector routes rather than canonical content permalinks
19	- Format bugs the rule-based layer doesn't catch (mojibake, inconsistent pluralization, truncated/wrapped cell content)
20
21	## Procedure
22
23	### Step 1: Gather sample data
24
25	```bash
26	# Locate research.json. Adjacent to the binary covers the post-promote
27	# layout (standalone polish, shipcheck against the library copy). The
28	# grandparent fallback covers mid-pipeline invocations where $CLI_DIR is
29	# $PRESS_RUNSTATE/runs/<id>/working/<cli> and research.json lives at
30	# $PRESS_RUNSTATE/runs/<id>/research.json. Without the fallback, scorecard
31	# reports `unable: true` mid-pipeline and we SKIP the most informative review.
32	# Use a bash array so the flag survives paths with spaces.
33	RESEARCH_ARGS=()
34	if [ ! -f "$CLI_DIR/research.json" ]; then
35	_grandparent="$(dirname "$(dirname "$CLI_DIR")")"
36	if [ -f "$_grandparent/research.json" ]; then
37	RESEARCH_ARGS=(--research-dir "$_grandparent")
38	fi
39	fi
40
41	cli-printing-press scorecard --dir "$CLI_DIR" "${RESEARCH_ARGS[@]}" --live-check --json > /tmp/output-review-livecheck.json 2>&1 \|\| true
42	```
43
44	If the scorecard call fails or `/tmp/output-review-livecheck.json` is empty, return the SKIP result (Step 3) without dispatching the reviewer.
45
46	### Step 2: Dispatch the reviewer agent
47
48	Use the Agent tool (general-purpose) with this prompt contract:
49
50	> Review the sampled outputs from the shipped CLI at `$CLI_DIR`. You have these ground-truth sources:
51	>
52	> - Sampled command output: read `/tmp/output-review-livecheck.json` and inspect the `live_check.features[]` array. Each entry has the command, example invocation, redacted stdout evidence (in `output_sample`, bounded to ~4 KiB), the redacted pass/fail reason, and a `warnings` array (populated by rule-based checks like the raw-HTML-entity detector). Treat `<redacted>` markers as privacy scrubbed values, not format bugs.
53	> - Review only `status: pass` entries. Entries with `status: fail` either crashed, timed out, or had placeholder args (`<id>`, `<url>`) that never produced real output — their sample is empty and there's nothing for you to judge. Phase 5 dogfood handles test-coverage and exit-code concerns.
54	> - `$CLI_DIR/research.json` `novel_features` (planned behavior per feature) and `novel_features_built` (verified built commands).
55	> - The CLI binary at `$CLI_DIR/<cli-name>-pp-cli` — you may invoke additional commands to gather more output when a finding needs verification.
56	>
57	> For each of these checks, report findings under 50 words each. Only report issues a human user would notice in 5 minutes of hands-on testing — not every edge case a thorough QA pass might find:
58	>
59	> 1. *Output semantically* matches query intent.** For sampled novel features with a query argument, judge relevance beyond what the mechanical query-token check in live-check already enforced. A feature that passed live-check's `

People who liked this also viewed

6 picks

Type

printing-press-output-review

4.6kinstalls453forks

View on GitHub

How to install printing-press-output-review?

mvanhorn/cli-printing-press/printing-press-output-review

$npx -y skills add mvanhorn/cli-printing-press --skill printing-press-output-review

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# printing-press-output-review (internal)
2
3	Review the sampled outputs from a printed CLI for plausibility bugs that dogfood, verify, and the rule-based `scorecard --live-check` rules can't catch. Wave B policy: all findings surface as warnings, never errors.
4
5	This skill is internal-only (`user-invocable: false`). It's invoked by parents — main printing-press skill at shipcheck Phase 4.85, polish skill during its diagnostic loop. Running it standalone would produce floating findings text with no ship verdict, no fixes applied, no publish offer; the actionable wrappers are `/printing-press` and `/printing-press-polish`. The skill carries `context: fork` so the reviewer agent's diagnostic chatter stays isolated from the calling skill's context.
6
7	## Input
8
9	The caller passes `$CLI_DIR` as the argument: an absolute path to the printed CLI's working directory.
10
11	## What this catches
12
13	Bugs that rule-based checks miss, typically surfaced by 5 minutes of hands-on testing but slipping past dogfood, verify, and `scorecard --live-check` rules:
14
15	- Substring-match results that coincidentally contain the query but don't match semantically (e.g., a query matches a substring of a larger unrelated term)
16	- Aggregation commands silently dropping sources when only some of the requested N come back
17	- Ranking or sort commands returning top-N results that aren't plausibly the best for the query (broken weights, extractor fallbacks)
18	- URLs in output pointing at category index pages, feed endpoints, or random-selector routes rather than canonical content permalinks
19	- Format bugs the rule-based layer doesn't catch (mojibake, inconsistent pluralization, truncated/wrapped cell content)
20
21	## Procedure
22
23	### Step 1: Gather sample data
24
25	```bash
26	# Locate research.json. Adjacent to the binary covers the post-promote
27	# layout (standalone polish, shipcheck against the library copy). The
28	# grandparent fallback covers mid-pipeline invocations where $CLI_DIR is
29	# $PRESS_RUNSTATE/runs/<id>/working/<cli> and research.json lives at
30	# $PRESS_RUNSTATE/runs/<id>/research.json. Without the fallback, scorecard
31	# reports `unable: true` mid-pipeline and we SKIP the most informative review.
32	# Use a bash array so the flag survives paths with spaces.
33	RESEARCH_ARGS=()
34	if [ ! -f "$CLI_DIR/research.json" ]; then
35	_grandparent="$(dirname "$(dirname "$CLI_DIR")")"
36	if [ -f "$_grandparent/research.json" ]; then
37	RESEARCH_ARGS=(--research-dir "$_grandparent")
38	fi
39	fi
40
41	cli-printing-press scorecard --dir "$CLI_DIR" "${RESEARCH_ARGS[@]}" --live-check --json > /tmp/output-review-livecheck.json 2>&1 \|\| true
42	```
43
44	If the scorecard call fails or `/tmp/output-review-livecheck.json` is empty, return the SKIP result (Step 3) without dispatching the reviewer.
45
46	### Step 2: Dispatch the reviewer agent
47
48	Use the Agent tool (general-purpose) with this prompt contract:
49
50	> Review the sampled outputs from the shipped CLI at `$CLI_DIR`. You have these ground-truth sources:
51	>
52	> - Sampled command output: read `/tmp/output-review-livecheck.json` and inspect the `live_check.features[]` array. Each entry has the command, example invocation, redacted stdout evidence (in `output_sample`, bounded to ~4 KiB), the redacted pass/fail reason, and a `warnings` array (populated by rule-based checks like the raw-HTML-entity detector). Treat `<redacted>` markers as privacy scrubbed values, not format bugs.
53	> - Review only `status: pass` entries. Entries with `status: fail` either crashed, timed out, or had placeholder args (`<id>`, `<url>`) that never produced real output — their sample is empty and there's nothing for you to judge. Phase 5 dogfood handles test-coverage and exit-code concerns.
54	> - `$CLI_DIR/research.json` `novel_features` (planned behavior per feature) and `novel_features_built` (verified built commands).
55	> - The CLI binary at `$CLI_DIR/<cli-name>-pp-cli` — you may invoke additional commands to gather more output when a finding needs verification.
56	>
57	> For each of these checks, report findings under 50 words each. Only report issues a human user would notice in 5 minutes of hands-on testing — not every edge case a thorough QA pass might find:
58	>
59	> 1. *Output semantically* matches query intent.** For sampled novel features with a query argument, judge relevance beyond what the mechanical query-token check in live-check already enforced. A feature that passed live-check's `

People who liked this also viewed

6 picks

Type