Aa resume

Skill Peeyushmeher/agent-agile/skills/aa-resume

Use when the user says resume, continue, or pick up where we left off, starts a new session on an existing Agent-Agile project, or is recovering after a crash or context reset, for example "/aa-resume", "let's continue", "where were we".From its SKILL.md

Install

npx -y skills add Peeyushmeher/agent-agile --skill aa-resume

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

3 stars3 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its file declares

Copied from the file, not written here

The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.

SKILL.md

1.9 KB, 420 tokens by cl100k_base, as published. Nobody here has run it

aa-resume

Resolve the Agent-Agile playbook root: use the first of these that exists — (1) ${CLAUDE_PLUGIN_ROOT}/playbooks, (2) ./.claude/agent-agile/playbooks, (3) ./.agents/agent-agile/playbooks, (4) ~/.claude/agent-agile/playbooks, (5) ~/.agents/agent-agile/playbooks, (6) ./playbooks.

Read playbooks/execution.md's "Resume protocol" section from that root, and follow it exactly:

If .planning/STATE.md does not exist, no project has been started here yet. Say so plainly, and point the user at the three front doors instead of guessing at a state that isn't there: a vague spark → /aa-grill, a clear idea → /aa-new-project, an existing plan or spec → /aa-import.
Otherwise, read .planning/STATE.md first and only. Don't re-derive status by re-reading the whole epic history — STATE.md is the baton, kept small on purpose so this step stays cheap every time.
Follow its pointers — at most three files — and read exactly those, nothing wider.
Continue the work from exactly where STATE.md says the run is: the phase it names (grill, intake, panel, prereqs, an epic's wave, review, or done), the "Now" sentence, and the "Next" sentence.
If STATE.md names a blocker, resolve or surface that blocker before doing anything else — never work around it silently.

Close the session, without exception, with one STATE.md update: what's in progress, what's next, the pointers the next session needs, and any blocker. A session that stops without this update leaves the next session to reconstruct state from scratch — the entire point of the baton is that this never has to happen.

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Gives 0 of the 12 instructions most hr recruiting skills give in 420 tokens

Counted across 356 of the 357 authors here whose files we hold, read 2026-08-07

Quantify achievements with specific metricsin 14 of 356, across 6 files
Keep the resume under two pagesin 14 of 356, across 6 files
Request the full job description if not providedin 12 of 356, across 4 files
Extract keywords and prioritize job requirementsin 12 of 356, across 4 files
Stop and ask for clarification if required inputs are missingin 12 of 356, across 5 files
Map candidate experience to job requirementsin 11 of 356, across 3 files
Ask if the user wants adjustmentsin 11 of 356, across 3 files
Provide strengths and gap analysis after the resumein 10 of 356, across 2 files
Request candidate background details if not providedin 10 of 356, across 2 files
Format experience bullets as action verb plus resultin 10 of 356, across 2 files
Ask for missing inputs before startingin 10 of 356, across 9 files
Use exact job description terminologyin 9 of 356, across 1 file

Said here and by no other author read

locate the playbook root
read the resume protocol
check for state file existence
follow state file pointers
resume work from named phase
resolve or surface named blockers

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.