mostafa-drz/claude-skills / code/emotional-recap
emotional-recap
VerifiedReviews the user's past Claude Code conversations from a wellbeing perspective — sentiment, tone, emotional arc, recurring patterns — and generates a supportive, science-grounded report in both Markdown and HTML. Default lookback is 48 hours across all projects. Uses recognised emotion frameworks (Plutchik, Ekman, Russell's circumplex, Pennebaker linguistic markers) and cites the science behind every observation. Learns the user's baseline tone over time so future reports flag genuine shifts, not noise. Use when the user asks for an emotional/wellbeing recap, mood check, sentiment review, or wants to understand their own ups and downs across recent work sessions.
| File | Kind | Size |
|---|---|---|
| DESIGN.md | markdown | 42.7 KB |
| SKILL.md | skill md | 25.7 KB |
| icon.svg | other | 481 B |
| reference/citations.md | markdown | 7.6 KB |
| reference/frameworks.md | markdown | 7.1 KB |
| reference/report-structure.md | markdown | 36.1 KB |
reference/citations.md
View on GitHub# Citations reference
Curated scientific references the report draws from. The skill picks a subset per `citation_depth` setting:
- `minimal` — 1-line refs inline, no full list at bottom
- `standard` — APA-style inline citations + a 5-item reference list
- `academic` — full reference list at bottom (~10 items), inline APA throughout
All entries below are real, peer-reviewed or widely-cited works. Do not invent citations; if you don't have the relevant ref here for a specific claim, drop the claim rather than fabricate.
---
## Emotion theory & taxonomy
**Plutchik, R. (1980).** _Emotion: A Psychoevolutionary Synthesis._ Harper & Row.
The wheel of emotions. Foundational for any discrete-emotion tagging.
**Ekman, P. (1992).** An argument for basic emotions. _Cognition & Emotion_, 6(3-4), 169-200.
The six basic emotions framework.
**Russell, J. A. (1980).** A circumplex model of affect. _Journal of Personality and Social Psychology_, 39(6), 1161-1178.
Valence × arousal dimensional model.
**Posner, J., Russell, J. A., & Peterson, B. S. (2005).** The circumplex model of affect: An integrative approach to affective neuroscience, cognitive development, and psychopathology. _Development and Psychopathology_, 17(3), 715-734.
Modern integration of Russell's model with neuroscience.
**Barrett, L. F. (2017).** _How Emotions Are Made: The Secret Life of the Brain._ Houghton Mifflin Harcourt.
The constructionist counterweight — emotion categories are not biologically fixed. Cite in caveats to keep the report intellectually honest.
---
## Linguistic markers & sentiment
**Pennebaker, J. W. (2003).** Telling stories: The health benefits of narrative. _Literature and Medicine_, 19(1), 3-18.
Linguistic markers of psychological state.
**Tausczik, Y. R., & Pennebaker, J. W. (2010).** The psychological meaning of words: LIWC and computerized text analysis methods. _Journal of Language and Social Psychology_, 29(1), 24-54.
The methods paper for LIWC-style analysis used throughout this skill.
**Rude, S., Gortner, E.-M., & Pennebaker, J. (2004).** Language use of depressed and depression-vulnerable college students. _Cognition & Emotion_, 18(8), 1121-1133.
The empirical basis for "rising 1st-person singular pronouns track with rumination / depressive cognition."
**Mohammad, S. M., & Turney, P. D. (2013).** Crowdsourcing a word–emotion association lexicon. _Computational Intelligence_, 29(3), 436-465.
The NRC Emotion Lexicon — basis for Plutchik-tag word lists.
---
## Wellbeing, flow, and positive psychology
**Csikszentmihalyi, M. (1990).** _Flow: The Psychology of Optimal Experience._ Harper & Row.
Used to reframe productive frustration. Engaged struggle ≠ distress.
**Fredrickson, B. L. (2001).** The role of positive emotions in positive psychology: The broaden-and-build theory of positive emotions. _American Psychologist_, 56(3), 218-226.
Why the "bright spots" section is required, not optional.
**Seligman, M. E. P., & Csikszentmihalyi, M. (2000).** Positive psychology: An introduction. _American Psychologist_, 55(1), 5-14.
The umbrella reference for the supportive framing of this skill.
---
## Sleep, circadian, and late-night work
**Walker, M. (2017).** _Why We Sleep: Unlocking the Power of Sleep and Dreams._ Scribner.
The pop-science synthesis. Cited when late-night sessions correlate with negative-valence drops.
**Yoo, S.-S., Gujar, N., Hu, P., Jolesz, F. A., & Walker, M. P. (2007).** The human emotional brain without sleep — a prefrontal amygdala disconnect. _Current Biology_, 17(20), R877-R878.
The empirical case: one night of sleep deprivation amplifies negative emotional reactivity by ~60%.
---
## Micro-experiments & actionable anchors (cited in §04 Worth trying)
These references back the **Worth trying** section. Each is a real peer-reviewed paper supporting a small, testable behaviour change. The skill must NOT generate Worth-trying items without a citation from this list or the lists above.
**Ariga, A., & Lleras, A. (2011).** Brief and rare mental "breaks" keep you focused: Deactivation and reactivation of task goals preempt vigilance decrements. _Cognition_, 118(3), 439-443.
Foundational for the "brief break restores attention" recommendation. Use when a frustration streak or attention-residue pattern is detected.
**Leroy, S. (2009).** Why is it so hard to do my work? The challenge of attention residue when switching between work tasks. _Organizational Behavior and Human Decision Processes_, 109(2), 168-181.
Attention residue across task switches. Use when single-project absorption + cross-project context-switching is detected.
**Lieberman, M. D., Eisenberger, N. I., Crockett, M. J., Tom, S. M., Pfeifer, J. H., & Way, B. M. (2007).** Putting feelings into words: Affect labeling disrupts amygdala activity in response to affective stimuli. _Psychological Science_, 18(5), 421-428.
The neuroscientific basis for "naming the emotion reduces its hold." Use when low emotional-vocabulary patterns surface — the action is to name the felt state, not to suppress it.
**Mauss, I. B., Tamir, M., Anderson, C. L., & Savino, N. S. (2011).** Can seeking happiness make people unhappy? Paradoxical effects of valuing happiness. _Emotion_, 11(4), 807-815.
Cite when patterns suggest the user is grading their own emotional state — caveat against making wellbeing itself a target.
**Sonnentag, S., & Fritz, C. (2007).** The recovery experience questionnaire: Development and validation of a measure for assessing recuperation and unwinding from work. _Journal of Occupational Health Psychology_, 12(3), 204-221.
Use when end-of-day patterns suggest poor detachment from work (e.g. late-night negative valence after intense daytime sessions).
**Killingsworth, M. A., & Gilbert, D. T. (2010).** A wandering mind is an unhappy mind. _Science_, 330(6006), 932.
Cite for present-moment-attention suggestions when mind-wandering / task-switching is implicated.
---
## Burnout & work-related stress (optional, used when patterns warrant)
**Maslach, C., & Leiter, M. P. (2016).** Understanding the burnout experience: recent research and its implications for psychiatry. _World Psychiatry_, 15(2), 103-111.
Reference for sustained negative-quadrant streaks across many sessions.
**Bakker, A. B., & Demerouti, E. (2007).** The job demands-resources model: state of the art. _Journal of Managerial Psychology_, 22(3), 309-328.
Framework for "demands vs resources" reframe when the user is consistently in high-arousal-negative.
---
## Caveats / scope-limiting
**Hutto, C. J., & Gilbert, E. (2014).** VADER: A parsimonious rule-based model for sentiment analysis of social media text. _Proceedings of ICWSM 2014._
Cite when explaining limits of text-sentiment analysis (sarcasm, brevity, domain shift).
**Barrett, L. F., Adolphs, R., Marsella, S., Martinez, A. M., & Pollak, S. D. (2019).** Emotional expressions reconsidered: Challenges to inferring emotion from human facial movements. _Psychological Science in the Public Interest_, 20(1), 1-68.
Cite (alongside Barrett 2017) when noting that the report is one signal, not a verdict.
---
## Selection rules
When choosing citations for a report:
1. **Always cite the framework being used** (Plutchik / Ekman / Russell / Pennebaker).
2. **For each pattern flagged**, cite the supporting paper from this list.
3. **Always include one caveat citation** (VADER or Barrett 2019) in the caveats section.
4. **At `academic` depth**, also include one positive-psychology citation (Fredrickson) in the bright-spots section.
5. Order the reference list **alphabetically by first author** in the final report.
Do not exceed `citation_depth` budget — fewer well-placed citations beats a wall of references.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |