diff --git a/plugin.yaml b/plugin.yaml index 7244cde..069e506 100644 --- a/plugin.yaml +++ b/plugin.yaml @@ -1,4 +1,4 @@ name: pstack -version: "0.3.1" +version: "0.3.3" description: "Poteto's engineering rigor stack. Playbooks, principles, multi-model review." author: poteto (adapted by Madeleine) diff --git a/skills/reflect/SKILL.md b/skills/reflect/SKILL.md index c2910ee..50e0604 100644 --- a/skills/reflect/SKILL.md +++ b/skills/reflect/SKILL.md @@ -53,6 +53,8 @@ Before applying any Accepted edit, present the synthesizer's full Accepted/Rejec Backlog items file to whatever devex / backlog tracker your team uses automatically. Only the Accepted list waits for approval. +Never edit a skill inside an installed plugin directory (for example `~/.hermes/plugins//skills/`). The next plugin update overwrites it. Before approval, show its destination: the active profile's skills directory (`~/.hermes/skills//`, or `~/.hermes/profiles//skills//` under a named profile). After approval, copy the skill folder there and edit the copy. Never open a PR or push. + For each approved Accepted item, follow the Routing field exactly: - Trivial existing-skill edit (a one-line bullet, a tightened sentence, a stale fact corrected): parent does directly. diff --git a/skills/sharpen/SKILL.md b/skills/sharpen/SKILL.md index 5069311..2e6c420 100644 --- a/skills/sharpen/SKILL.md +++ b/skills/sharpen/SKILL.md @@ -1,7 +1,7 @@ --- name: sharpen -description: "Sharpen a task's framing before starting the work." -version: 0.1.0 +description: "Make a prompt deeper, not bigger, then rewrite it." +version: 0.2.0 author: poteto (Hermes adaptation) license: MIT platforms: [linux, macos, windows] @@ -11,4 +11,13 @@ metadata: related_skills: [] --- -Before starting, ask how a top expert would approach this task (their raw sources, their real methods, an outside check that the result is right), what the user is really after, and whether the task is over- or underspecified. Loosen constraints that don't serve the goal as readily as you add ones that do, and leave choices that are the user's to make open instead of deciding them. Fold in only what makes the work better, not bigger, but always keep one outside check that the result is right, without narrating the framing, then do the work. +I want a deeper version of this task, not a bigger one. Before rewriting it, do four things: + +1. Say what a top professional in this field would do here that I'm not asking for. +2. Name the rawest material they would start from instead of what has already been digested for me. +3. Name the specific methods and tools they would use. +4. Say what, other than you or me, would show the result is right. + +Then rewrite my prompt to ask for exactly that. Return only the rewritten prompt. Do not do the task. + +Leave choices that are mine to make open instead of deciding them.