Feature/4 implement skill pr review

.github/copilot-instructions.md

@@ -4,14 +4,3 @@
 
 When reviewing a pull request, load and apply:
 https://github.com/AbsaOSS/agentic-toolkit/blob/master/skills/pr-review/SKILL.md
-
-### Skill-specific checks — apply when any `SKILL.md` is modified
-
-For every modified `SKILL.md`, also verify:
-- `name` is kebab-case, matches the directory name, and is ≤ 64 chars
-- `description` covers both "what it does" AND "when to trigger" with explicit trigger keywords
-- `description` is ≤ 1024 chars and not padded with filler
-- SKILL.md body is < 500 lines, or uses progressive disclosure via `references/`
-- No hardcoded credentials, secrets, or absolute internal paths in skill body or scripts
-- Any bundled script in `scripts/` is referenced from SKILL.md with clear usage guidance
-- The new or modified skill's description does not conflict with or shadow existing skills

.github/workflows/check_pr_release_notes.yml

@@ -21,3 +21,4 @@ jobs:
           github-repository: ${{ github.repository }}
           pr-number: ${{ github.event.number }}
           skip-labels: "no RN"
+          title: "## [Rr]elease [Nn]otes"

CONTRIBUTING.md

@@ -227,5 +227,6 @@ Before opening a pull request, verify:
 - [ ] No hardcoded credentials, secrets, or internal paths in skill body or scripts
 - [ ] Any script in `scripts/` is referenced from `SKILL.md` with usage guidance
 - [ ] New skill's description does not conflict with or shadow existing skills
+- [ ] Skill added to the catalog table in `README.md`
 - [ ] Evals exist (or a note explains why they are not applicable)
 - [ ] `skills-ref validate ./skills/my-skill` passes (install: `pip install skills-ref`)

README.md

@@ -75,7 +75,10 @@ For the full guide — what skills are, how they activate, project-scoped instal
 Browse all available skills in the **[skills/](./skills/)** directory — each skill folder contains a `SKILL.md` with
 its purpose, trigger phrases, and full instructions.
 
-> The catalog table will be populated as skills are added. See `skills/` for the current set.
+| Skill                                                | Description                                                                                                                         |
+|------------------------------------------------------|-------------------------------------------------------------------------------------------------------------------------------------|
+| **[pr-review](./skills/pr-review/)**                 | Pull request code review — reviews diffs for risk, security issues, API contract changes, dependency bumps, CI/CD and infrastructure changes. Produces concise Blocker / Important / Nit comments. |
+| **[token-saving](./skills/token-saving/)**           | Always-active response discipline — enforces brevity, no filler openers or closers, structured output, and a What/Why/How footer on code responses. Suspends on explicit "full detail" requests. |
 
 ## Finding More Skills
 
@@ -87,7 +90,7 @@ Before building a new skill, check whether one already exists:
 | [skills.sh](https://skills.sh)                                                       | Open registry — install with `npx skills add <owner/repo>`              |
 | [anthropics/skills](https://github.com/anthropics/skills)                            | Anthropic reference skills including `skill-creator`                    |
 | [absa-group/agent-skills](https://github.com/absa-group/agent-skills)                | Broader ABSA-owned skill collection                                     |
-| [absa-group/cps-agentic-toolkit](https://github.com/absa-group/cps-agentic-toolkit)  | CPS team's skill set built on top of this repo                          |
+| [absa-group/cps-agentic-toolkit](https://github.com/absa-group/cps-agentic-toolkit)  | CPS team's extended skill set (ABSA-internal)                           |
 
 ## Contributing
 
@@ -116,3 +119,4 @@ Claude, Cursor, Windsurf, and custom pipelines.
 ## Troubleshooting
 
 Setup issues and common fixes are covered in **[docs/troubleshooting.md](./docs/troubleshooting.md)**.
+All documentation guides are indexed at **[docs/](./docs/)**.

docs/README.md

@@ -2,13 +2,22 @@
 
 Navigation hub for all guides in this repository. Browse by category below.
 
-| Guide                                   | Audience | Description                                                                        |
-|-----------------------------------------|----------|------------------------------------------------------------------------------------|
-| [Getting Started](./getting-started.md) | Users    | What skills are, how to install them, Copilot CLI usage                            |
-| [Troubleshooting](./troubleshooting.md) | Users    | Setup guides and fixes for install, activation, and proxy issues                   |
-| [Contributing](../CONTRIBUTING.md)      | Authors  | Skill folder layout, frontmatter, description writing, body guidelines, PR process |
-| [Skill Testing](./skill-testing.md)     | Authors  | Eval creation, fixtures, regression loops, trigger and description optimization    |
-
-> **Keep this index up to date.** When you add a new guide under `docs/`, add a row to the table above.
+## Setup & Repository Guides
+
+| Guide                                   | Description                                                                         |
+|-----------------------------------------|-------------------------------------------------------------------------------------|
+| [Getting Started](./getting-started.md) | What skills are, how to install them, Copilot CLI usage                             |
+| [Contributing](../CONTRIBUTING.md)  | Skill folder layout, frontmatter, description writing, body guidelines, PR process |
+| [Skill Testing](./skill-testing.md) | Eval creation, fixtures, regression loops, trigger and description optimization    |
+| [Troubleshooting](./troubleshooting.md) | Setup fixes for install, activation, and proxy issues                               |
+
+## Skill Guides
+
+| Guide                               | Description                                                                        |
+|-------------------------------------|------------------------------------------------------------------------------------|
+| [PR Review](./pr-review.md)             | How the PR review skill works, what sections it applies, and how to trigger it     |
+| [Token Saving](./token-saving.md)       | Keeping AI responses concise — how the token-saving skill works and when it applies |
+
+> **Keep this index up to date.** When you add a new guide, add a row to the appropriate table above.
 
 See also the [main README](../README.md) for the skill catalog, scope, and FAQ.

docs/getting-started.md

@@ -132,7 +132,7 @@ Project skills take precedence over global skills when both exist.
 ### Add project-specific skills
 
 For skills that only apply to a specific repository, place them in `.github/skills/` within that repo. These are loaded
-automatically when Copilot CLI is launched from that directory, layered on top of your personal and CPS base skills.
+automatically when Copilot CLI is launched from that directory, layered on top of your personal and shared base skills.
 
 ```
 your-project-repo/

docs/pr-review.md

@@ -0,0 +1,101 @@
+# PR Review Skill
+
+The `pr-review` skill performs structured, risk-aware code review on pull requests and diffs. It activates automatically when you ask for PR feedback, share a diff, or ask for a sanity check on changes.
+
+---
+
+## What it does
+
+The skill reads the list of files changed in a PR, selects the relevant review sections, and produces a concise review grouped by severity:
+
+| Severity | Meaning |
+|----------|---------|
+| **Blocker** | Must be fixed before merge — correctness bug, security vulnerability, broken contract, credentials in code, data loss risk |
+| **Important** | Should be fixed soon — increases risk, missing tests for changed logic, non-default that's hard to change later |
+| **Nit** | Minor polish — style, naming, optional improvement, non-urgent edge case |
+
+If a section has no findings, the skill writes `_None._` to show it was checked, not skipped.
+
+---
+
+## Sections
+
+The skill always applies **Standard review** and selects additional sections based on the files the PR touches:
+
+| Section | Triggers when PR touches |
+|---|---|
+| Standard | Always applied |
+| API contracts | Endpoints, DTOs, config keys, env vars, exit codes, output strings |
+| Dependency bumps | `pom.xml`, `requirements.txt`, `pyproject.toml`, `package.json`, `*.csproj`, `go.mod`, `build.sbt` |
+| CI/CD | `.github/workflows/`, `Jenkinsfile`, `Justfile`, `Makefile` (pipeline), deployment jobs |
+| Infrastructure | `*.tf`, `*.tfvars`, CloudFormation, Helm, Dockerfiles, `docker-compose.yml`, `iac/`, `infra/` |
+| DB migrations | `alembic/`, `flyway/`, `liquibase/`, `migrations/`, `*.sql`, `db/` |
+| Elevated risk | Overlay — applied on top when PR touches auth, security controls, secrets management, or is a wide refactor (≥ 10 call sites) |
+
+A file may match multiple sections — all matching sections are applied.
+
+---
+
+## How to trigger it
+
+Ask for a review naturally — the skill fires on intent, not exact wording:
+
+```
+review my PR
+any issues with these changes?
+LGTM?
+does this look right?
+check this diff for risks
+can you review this before I merge?
+```
+
+You can also share a GitHub PR link directly:
+
+```
+https://github.com/org/repo/pull/123 — does this look safe to merge?
+```
+
+> **Does NOT trigger** for generative tasks on a diff: "generate release notes from this diff", "summarise this diff". Those are documentation tasks.
+
+---
+
+## Helpers
+
+The skill ships two scripts to speed up data gathering:
+
+| Script | Purpose |
+|--------|---------|
+| `scripts/fetch_pr.sh <PR_NUMBER>` | Fetches the diff and file list via `gh` |
+| `scripts/classify_sections.py /tmp/pr_files.txt` | Prints which sections to apply given a file list |
+
+These require the [GitHub CLI](https://cli.github.com/) (`gh`) to be authenticated.
+
+---
+
+## Overriding or scoping the review
+
+You can narrow or redirect the review with natural language:
+
+```
+focus only on security issues
+skip the nits — just blockers and importants
+review only the migration files
+```
+
+---
+
+## Installation
+
+The skill is installed along with the rest of the toolkit:
+
+```bash
+npx skills add https://github.com/AbsaOSS/agentic-toolkit -g
+```
+
+To install only this skill:
+
+```bash
+npx skills add https://github.com/AbsaOSS/agentic-toolkit -g --skill pr-review
+```
+
+See [Getting Started](./getting-started.md) for the full install guide.

docs/token-saving.md

@@ -0,0 +1,71 @@
+# Token-Saving Skill
+
+The `token-saving` skill enforces concise, low-noise AI responses. It is **always active** — it applies to every reply without needing to be triggered by a specific phrase.
+
+---
+
+## What it changes
+
+Without the skill, AI assistants commonly pad responses with filler openers, closing platitudes, and repeated context. This skill removes that noise.
+
+| Behaviour | Without skill | With skill |
+|-----------|--------------|------------|
+| Response opener | "Great question! Certainly, I'd be happy to help..." | Directly answers |
+| Closing | "Let me know if you have any questions!" | Stops when done |
+| Repeated context | Restates what you just said | Skips it |
+| Factual answers | Unlimited prose | ≤ 5 lines |
+| Action lists | Unlimited bullets | Capped at 4 |
+| Full file dumps | Common | Only when you ask |
+
+---
+
+## Code output footer
+
+Every response that writes or changes code ends with exactly this footer — no more, no less:
+
+```
+**What changed:** <one line>
+**Why:** <one line>
+**How to verify:** <command or test instruction>
+```
+
+This applies to: new functions, patches, inline diffs, config snippets, or any code block representing a change.
+
+It does **not** apply to: Q&A, reviews, planning, comparisons, or conceptual explanations.
+
+---
+
+## Overriding the skill
+
+The brevity rules suspend for a single response when you explicitly ask for depth:
+
+> "Give me a full explanation."
+> "Deep dive into this."
+> "Don't hold back."
+> "Complete explanation."
+
+The next response is fully unrestricted. Rules resume after that.
+
+---
+
+## Precedence
+
+If another active skill specifies its own output format (e.g. a review skill with a Blocker / Important / Nit structure), that format takes precedence over this skill's rules.
+
+---
+
+## Installation
+
+The skill is installed along with the rest of the toolkit:
+
+```bash
+npx skills add https://github.com/AbsaOSS/agentic-toolkit -g
+```
+
+To install only this skill:
+
+```bash
+npx skills add https://github.com/AbsaOSS/agentic-toolkit -g --skill token-saving
+```
+
+See [Getting Started](./getting-started.md) for the full install guide.